[
  {
    "case_id": "fb7725c351ba",
    "name": "提杠铃 · Barbell lift",
    "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
    "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
    "outputs": [
      {
        "status": "complete",
        "case_id": "fb7725c351ba",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
        "prompt_rewriting": false,
        "seed": 2026081901,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": null,
        "expert_usage_assertion_passed": true,
        "prompt_capture_assertion_passed": true,
        "full_decode_passed": true,
        "output": {
          "sha256": "cb9a41e6af23c63dfcc99430a4c56ba498e97dca5a0f29f3777d6dc47fb5dc32",
          "width": 832,
          "height": 480,
          "avg_frame_rate": "25/1",
          "nb_read_frames": "81"
        },
        "elapsed_seconds": null,
        "completed_utc": "2026-09-23T19:40:28.952388+00:00",
        "job": "214649",
        "hostname": "auh7-1b-gpu-255",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "cf5e73c03b21c57f4ca93a4bfbdd3f6935a35fa3f9e8687736845df1712c49f6",
        "receipt_recovery": {
          "reason": "Generated video was valid; unsupported compute-node ffprobe wrapper arguments stopped post-processing.",
          "observed_failure": "ffprobe subprocess after prompt/expert assertions, encode, and complete ffmpeg decode",
          "log_path": "logs/bernini-214649.log",
          "log_sha256": "09c0b4103a2a88d1aaa3c0cb0920acb36ad744a54a0371abc6238423ce9b004a",
          "driver_path": "provenance/drivers_v1/run_bernini.py",
          "missing_runtime_measurements": [
            "per-expert forward counts",
            "elapsed_seconds",
            "positive_token_count"
          ],
          "validation": "Independent complete local ffmpeg decode and genuine ffprobe frame count; no video regenerated or replaced."
        },
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "source_reference_frames": [],
        "prompt_truncated": false,
        "positive_token_count": null,
        "positive_token_count_assertion_passed": true,
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ]
      },
      {
        "status": "complete",
        "case_id": "fb7725c351ba",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
        "prompt_rewriting": false,
        "seed": 2026081901,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": null,
        "expert_usage_assertion_passed": true,
        "prompt_capture_assertion_passed": true,
        "full_decode_passed": true,
        "output": {
          "sha256": "824308c194214741551ae419983cf4c8b2cf0690b1e50d656383ad01d16d86df",
          "width": 832,
          "height": 480,
          "avg_frame_rate": "25/1",
          "nb_read_frames": "81"
        },
        "elapsed_seconds": null,
        "completed_utc": "2026-09-23T19:53:48.570684+00:00",
        "job": "214677",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "3e34e9031fb4622896f5ac2765f6c15fcf8740324100c341cf70fb5bb71bba7d",
        "receipt_recovery": {
          "reason": "Generated video was valid; unsupported compute-node ffprobe wrapper arguments stopped post-processing.",
          "observed_failure": "ffprobe subprocess after prompt/expert assertions, encode, and complete ffmpeg decode",
          "log_path": "logs/omni-canary2-214677.log",
          "log_sha256": "7de41d5e17edbdb8498006657ad0723392a68896346d72d1856589bbcdd56635",
          "driver_path": "provenance/drivers_v1/run_omni.py",
          "missing_runtime_measurements": [
            "per-expert forward counts",
            "elapsed_seconds",
            "negative T5 text not separately persisted; its equality assertion passed"
          ],
          "validation": "Independent complete local ffmpeg decode and genuine ffprobe frame count; no video regenerated or replaced."
        },
        "actual_t5_text": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "qwen_features": {
          "case_id": "fb7725c351ba",
          "arm": "t2v",
          "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
          "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            53,
            2048
          ],
          "feature_sha256": "09257c22c470b91a506cd2f6e96df101e6f138ae2fd62cacc9851d82cd597b7c"
        },
        "t5_text_inputs": [
          "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible."
        ],
        "positive_t5_context_copies": 1,
        "visual_latent_shape": null,
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "total_forward_count_assertion": 80
      },
      {
        "status": "complete",
        "case_id": "fb7725c351ba",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 107,
        "prompt_truncated": false,
        "seed": 2026081901,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/fb7725c351ba/source-exact81.mp4",
        "source_sha256": "479ee891773dfffc3299149103ee2ef37f4bb63f213b1c4c7cbd5391ebd4704a",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_min",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "6b544f44db85d07a6f1792758ccb4d4ff2f2482cdf42348661ddf06c33f79575",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:22:14.144770+00:00",
        "elapsed_seconds": 2187.05,
        "job": "214692",
        "hostname": "auh7-1b-gpu-289",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "3b0d2856c6329312cd3627b4df0028cafb7902121d323ef0cdd46ea580f4a200"
      },
      {
        "status": "complete",
        "case_id": "fb7725c351ba",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
        "actual_t5_text": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "fb7725c351ba",
          "arm": "editing",
          "caption": "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
          "caption_sha256": "b3337cc9b01e086c7969770d68fc6c6572e454e5fe1be64f770a6b7e1e30500d",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/fb7725c351ba/source-exact81.mp4",
          "source_sha256": "479ee891773dfffc3299149103ee2ef37f4bb63f213b1c4c7cbd5391ebd4704a",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            80,
            2048
          ],
          "feature_sha256": "0f447b68b39d44f6134f90a6a56244778144a651f3c807fce44417faed46405a"
        },
        "t5_text_inputs": [
          "The woman in a home gym lifts a barbell from the floor to her waist. She wears black activewear. The home gym has a tiled floor and exercise equipment. A static full-body shot keeps the woman and the barbell visible.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081901,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/fb7725c351ba/source-exact81.mp4",
        "source_sha256": "479ee891773dfffc3299149103ee2ef37f4bb63f213b1c4c7cbd5391ebd4704a",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "e66930bf62f233054b25761f5b614ac725f044c20ac7179ecca273b7b092493f",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:14:05.087905+00:00",
        "elapsed_seconds": 932.32,
        "job": "214720",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "3fadbe0c2961",
    "name": "狗转头 · Dog head turn",
    "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
    "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
    "outputs": [
      {
        "status": "complete",
        "case_id": "3fadbe0c2961",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 63,
        "prompt_truncated": false,
        "seed": 2026081902,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_min",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "dc894ddffe1960fa0a845b2bbf03c37162d8b496e887ef535bed5cbf2ace9616",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:45:29.419504+00:00",
        "elapsed_seconds": 706.21,
        "job": "214706",
        "hostname": "auh7-1b-gpu-269",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "3fadbe0c2961",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
        "actual_t5_text": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "3fadbe0c2961",
          "arm": "t2v",
          "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
          "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            51,
            2048
          ],
          "feature_sha256": "13a1edc8e7db94239ea6c6049d5691001949d9c95c3900fb5bbfd9298401f18a"
        },
        "t5_text_inputs": [
          "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081902,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "e92d7a1bcddf3582e33dbd1b93244e9a12de37a18ea27ffff2088f026e3584ec",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:35:53.507686+00:00",
        "elapsed_seconds": 637.05,
        "job": "214727",
        "hostname": "auh7-1b-gpu-307",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "3fadbe0c2961",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 102,
        "prompt_truncated": false,
        "seed": 2026081902,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/3fadbe0c2961/source-exact81.mp4",
        "source_sha256": "99170f8a711a3d5a3e930a995561646ac557366cf92f5ded7ac13c6a986f8364",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "sigma_max",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "59ddf05fd48e62dffbc27aac5a721cb7198c40d526c06479056695547d9cf48f",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:49:23.038345+00:00",
        "elapsed_seconds": 1621.77,
        "job": "214751",
        "hostname": "auh7-1b-gpu-307",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "3fadbe0c2961",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
        "actual_t5_text": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "3fadbe0c2961",
          "arm": "editing",
          "caption": "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
          "caption_sha256": "aaeb58cbd788e3a815962e6289b1853ca09f2ef13c69d98a1af484e67f9da178",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/3fadbe0c2961/source-exact81.mp4",
          "source_sha256": "99170f8a711a3d5a3e930a995561646ac557366cf92f5ded7ac13c6a986f8364",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            78,
            2048
          ],
          "feature_sha256": "5607250394671775f7a81e3929b7e9ff08652121e7def64d0a370240e1f6e2ce"
        },
        "t5_text_inputs": [
          "The dog turns its head further to the right while sitting in the grass. The dog is a reddish-brown and white Pembroke Welsh Corgi in a sunny green field. The camera is stationary in a medium shot.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081902,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/3fadbe0c2961/source-exact81.mp4",
        "source_sha256": "99170f8a711a3d5a3e930a995561646ac557366cf92f5ded7ac13c6a986f8364",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "87aa2a665e5c451327950cf7eaa217e0f10ba00a2dac3f85af22489eb046501b",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:07:32.501671+00:00",
        "elapsed_seconds": 637.79,
        "job": "214739",
        "hostname": "auh7-1b-gpu-282",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "7077cfb160cf",
    "name": "长椅上写字 · Write in notebook",
    "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
    "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
    "outputs": [
      {
        "status": "complete",
        "case_id": "7077cfb160cf",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 68,
        "prompt_truncated": false,
        "seed": 2026081904,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "shift_terminal",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "eaf121f7e20fa7dc7aa6d4d127b00180cb92fee67e1fdea5ff2fbc7b9be7d997",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:19:58.997189+00:00",
        "elapsed_seconds": 705.61,
        "job": "214757",
        "hostname": "auh7-1b-gpu-269",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "7077cfb160cf",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
        "actual_t5_text": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "7077cfb160cf",
          "arm": "t2v",
          "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
          "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            53,
            2048
          ],
          "feature_sha256": "863e64e016115388d775caa7fd1a8be61270b967361152418dfda43d47ba5cc6"
        },
        "t5_text_inputs": [
          "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081904,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "cfce2698573f7b20a42686a08059ff6d39d7053cafcf4731fddab4d174c804ae",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:35:38.009473+00:00",
        "elapsed_seconds": 599.71,
        "job": "214728",
        "hostname": "auh7-1b-gpu-283",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "7077cfb160cf",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 107,
        "prompt_truncated": false,
        "seed": 2026081904,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7077cfb160cf/source-exact81.mp4",
        "source_sha256": "cef4c183b459c8aad72cdc81f3e6b2766a36fc22156bf382dd36c29cec6d5aa9",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "sigma_min",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "2b0371a6e0660520daf895823f2f74b556503b075578fe2dca02f5c398bd23e7",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:05:32.304246+00:00",
        "elapsed_seconds": 2298.97,
        "job": "214752",
        "hostname": "auh7-1b-gpu-210",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "7077cfb160cf",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
        "actual_t5_text": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "7077cfb160cf",
          "arm": "editing",
          "caption": "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
          "caption_sha256": "0acdffedc18b04d2c2bef7d0a4e4e51544b75d4dd1f904e080d9e0490be24fb1",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7077cfb160cf/source-exact81.mp4",
          "source_sha256": "cef4c183b459c8aad72cdc81f3e6b2766a36fc22156bf382dd36c29cec6d5aa9",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            80,
            2048
          ],
          "feature_sha256": "70de5d8bbce06459f31e50438e02db4aae638a7c14eec75b64875ee09eb289cb"
        },
        "t5_text_inputs": [
          "The young woman sitting on a park bench thoughtfully writes in her notebook with a pen. She has shoulder-length light brown hair and wears a pink shirt and blue jeans. The wooden bench is in a sunny park. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081904,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7077cfb160cf/source-exact81.mp4",
        "source_sha256": "cef4c183b459c8aad72cdc81f3e6b2766a36fc22156bf382dd36c29cec6d5aa9",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "3b158d997abb43e583b01b618a280bb0938570e81b73116ce351f2cb255e96af",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:08:05.180195+00:00",
        "elapsed_seconds": 649.79,
        "job": "214740",
        "hostname": "auh7-1b-gpu-313",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "7e488525099e",
    "name": "转身倚车 · Turn and lean on car",
    "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
    "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
    "outputs": [
      {
        "status": "complete",
        "case_id": "7e488525099e",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 58,
        "prompt_truncated": false,
        "seed": 2026081906,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "sigma_min",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "4d3b693a341087b216eba42bc9933ed61efbead441536c78638dfd4e5cca9145",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:17:05.780853+00:00",
        "elapsed_seconds": 519.14,
        "job": "214758",
        "hostname": "auh7-1b-gpu-312",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "7e488525099e",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
        "actual_t5_text": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "7e488525099e",
          "arm": "t2v",
          "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
          "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            44,
            2048
          ],
          "feature_sha256": "9f6d9a9afe61984fcb7355e65810471e2b4b623b73134d18a47daa0936b86b83"
        },
        "t5_text_inputs": [
          "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081906,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "5d79f8d88fc14bccd0336603594e03abcc72413534b835b37698aed74b1bc7cf",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:36:39.023949+00:00",
        "elapsed_seconds": 615.52,
        "job": "214729",
        "hostname": "auh7-1b-gpu-313",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "7e488525099e",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 97,
        "prompt_truncated": false,
        "seed": 2026081906,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7e488525099e/source-exact81.mp4",
        "source_sha256": "1f3cec72bef55b67c15ebfc063252cce867ea128594a225db61688ff961b35d4",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_min",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "9829080372e3351bb3375d787615f72cc4a10be693f382edd9d36fae37079d0e",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:38:14.312525+00:00",
        "elapsed_seconds": 2268.32,
        "job": "214753",
        "hostname": "auh7-1b-gpu-221",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "7e488525099e",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
        "actual_t5_text": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "7e488525099e",
          "arm": "editing",
          "caption": "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
          "caption_sha256": "ed6115b291eb39710054250e5a6fd3e51f92ed3675fe1af1c5b45617396c3082",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7e488525099e/source-exact81.mp4",
          "source_sha256": "1f3cec72bef55b67c15ebfc063252cce867ea128594a225db61688ff961b35d4",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            71,
            2048
          ],
          "feature_sha256": "a34cbe81e1903e91618292d5ab323f49478f88c4638de853db8d3bb4475d4242"
        },
        "t5_text_inputs": [
          "The woman in a black leather jacket and red pants turns and leans back against the hood of the black car. The setting is an underground parking garage with steady red lighting. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081906,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7e488525099e/source-exact81.mp4",
        "source_sha256": "1f3cec72bef55b67c15ebfc063252cce867ea128594a225db61688ff961b35d4",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "19321c8236ea55c3ce3006817c0c8316f9313bc193729e4ba6dd1651f445d5fc",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:15:57.054117+00:00",
        "elapsed_seconds": 886.52,
        "job": "214741",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "d5221a1b69d5",
    "name": "闭眼尝汤 · Taste from ladle",
    "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
    "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
    "outputs": [
      {
        "status": "complete",
        "case_id": "d5221a1b69d5",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 53,
        "prompt_truncated": false,
        "seed": 2026081907,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_min",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "28120017a5e122b3f72956b9c2b16b20aae762baa4e88b9bab605ed03fff7c40",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:42:17.028942+00:00",
        "elapsed_seconds": 483.92,
        "job": "214709",
        "hostname": "auh7-1b-gpu-312",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "d5221a1b69d5",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
        "actual_t5_text": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "d5221a1b69d5",
          "arm": "t2v",
          "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
          "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            40,
            2048
          ],
          "feature_sha256": "32fb5857a4b6f85b7d8f9028089619067c830e83ddb787da525a2475cfdcbf7c"
        },
        "t5_text_inputs": [
          "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081907,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "9ee4d254b5c2d579d3a9adcdc9d1057d7a8ef0afe1860f8a785db66d2cedd8ab",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:36:30.235433+00:00",
        "elapsed_seconds": 603.1,
        "job": "214730",
        "hostname": "auh7-1b-gpu-282",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "d5221a1b69d5",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 92,
        "prompt_truncated": false,
        "seed": 2026081907,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d5221a1b69d5/source-exact81.mp4",
        "source_sha256": "fdd1b3df4b94449dc59cd04d03deb769fb2cf6c4c2d7b87221e2b3a6b5557d14",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "shift_terminal",
            "sigma_min"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "9cdbd07566d899630c7d460876abe733604cb04d284adf01842a9716a5db4ec3",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:38:07.139056+00:00",
        "elapsed_seconds": 2248.64,
        "job": "214754",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "d5221a1b69d5",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
        "actual_t5_text": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "d5221a1b69d5",
          "arm": "editing",
          "caption": "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
          "caption_sha256": "043306a7c3eff9ad7a50db5bbf0d3b4a2d6dec27fb8c5b5f6a316382992bc71b",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d5221a1b69d5/source-exact81.mp4",
          "source_sha256": "fdd1b3df4b94449dc59cd04d03deb769fb2cf6c4c2d7b87221e2b3a6b5557d14",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            67,
            2048
          ],
          "feature_sha256": "c34f3a4e8b0058cf7a7f941082a5266c00ee63aea17fccbbdec08c7d9905eddb"
        },
        "t5_text_inputs": [
          "The woman in an apron closes her eyes as she tastes from a metal ladle. She wears a patterned apron in a modern kitchen. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081907,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d5221a1b69d5/source-exact81.mp4",
        "source_sha256": "fdd1b3df4b94449dc59cd04d03deb769fb2cf6c4c2d7b87221e2b3a6b5557d14",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "a1e43492995e5fefe7ace547ce6f62cb6fe363ae29ad365f7144f36f7bf4e900",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:23:04.739246+00:00",
        "elapsed_seconds": 963.54,
        "job": "214742",
        "hostname": "auh7-1b-gpu-210",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "40712e1341dc",
    "name": "放下手机后翻身睡觉 · Put phone away and sleep",
    "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
    "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
    "outputs": [
      {
        "status": "complete",
        "case_id": "40712e1341dc",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 74,
        "prompt_truncated": false,
        "seed": 2026081911,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "sigma_max",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "ac158010a45d2c746774740d9a513440d29ac8d82604895d75b41c73e1461eef",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:45:13.322144+00:00",
        "elapsed_seconds": 482.84,
        "job": "214710",
        "hostname": "auh7-1b-gpu-283",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "40712e1341dc",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
        "actual_t5_text": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "40712e1341dc",
          "arm": "t2v",
          "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
          "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            61,
            2048
          ],
          "feature_sha256": "f953db0ef97435bed85eb46eb0a25136e1775f7d4342e1a435a9ed189580145c"
        },
        "t5_text_inputs": [
          "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081911,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "9dafe547fd5b649dccbf097319e9f41141518721416a7a75534548dbf4f138e3",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:26:43.210982+00:00",
        "elapsed_seconds": 958.87,
        "job": "214756",
        "hostname": "auh7-1b-gpu-210",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "40712e1341dc",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 113,
        "prompt_truncated": false,
        "seed": 2026081911,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/40712e1341dc/source-exact81.mp4",
        "source_sha256": "654e997c46a6f78a2ad78359b713767aefe61a6cc732b5be4527720323349f69",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_max",
            "sigma_min"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "d6b8387a8f977f88fec1fa6f16ef0ad0ae9c22554a74bb661014ad6260532037",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T22:30:33.960692+00:00",
        "elapsed_seconds": 1605.68,
        "job": "214755",
        "hostname": "auh7-1b-gpu-283",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "40712e1341dc",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
        "actual_t5_text": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "40712e1341dc",
          "arm": "editing",
          "caption": "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
          "caption_sha256": "24857d19e619899acd653ea104c6a5b68b895cdd4b5cc3637df661f694521907",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/40712e1341dc/source-exact81.mp4",
          "source_sha256": "654e997c46a6f78a2ad78359b713767aefe61a6cc732b5be4527720323349f69",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            88,
            2048
          ],
          "feature_sha256": "17f26bdae837dadcbf1c11b139c2c9ba8cbaa805f2f35c4fff16b1a5a0a45f67"
        },
        "t5_text_inputs": [
          "The man in bed puts his smartphone on the nightstand and turns over to go to sleep. He has dyed-blond hair, wears a pink tank top and a nose ring, and is in a dark bedroom with a nightstand beside the bed. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081911,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/40712e1341dc/source-exact81.mp4",
        "source_sha256": "654e997c46a6f78a2ad78359b713767aefe61a6cc732b5be4527720323349f69",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "271248625a365fabc0664f1e5f3cfadd94ad2179e17a2efa261b9d5926d3765b",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:20:56.467352+00:00",
        "elapsed_seconds": 646.24,
        "job": "214743",
        "hostname": "auh7-1b-gpu-307",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "10af6c651dbc",
    "name": "Jellyfish contraction",
    "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
    "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
    "outputs": [
      {
        "status": "complete",
        "case_id": "10af6c651dbc",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 65,
        "prompt_truncated": false,
        "seed": 2026081910,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_min",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "99c080cb8ebc719e47354dbc79ba641c7ffcc30c355bbafd05335903314ba8d8",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:04:25.056432+00:00",
        "elapsed_seconds": 579.95,
        "job": "214700",
        "hostname": "auh7-1b-gpu-282",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "10af6c651dbc",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
        "actual_t5_text": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "10af6c651dbc",
          "arm": "t2v",
          "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
          "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            47,
            2048
          ],
          "feature_sha256": "b1d9193dbd160064ceb99196242d2707a2f74e510993302982dac03e6b713c01"
        },
        "t5_text_inputs": [
          "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081910,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "1d1edd0eef41ff1fcde1a1bd662fdb47694a3b9ed60e458e83e842af441f9eb6",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:18:02.505227+00:00",
        "elapsed_seconds": 608.46,
        "job": "214721",
        "hostname": "auh7-1b-gpu-312",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "10af6c651dbc",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 104,
        "prompt_truncated": false,
        "seed": 2026081910,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/10af6c651dbc/source-exact81.mp4",
        "source_sha256": "ea86ef53e403f1cc602594cc3623a2fb66fb9b2f65c1461ef2bf62bee82a35fb",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "sigma_min",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "82c8810cd7546c2d6ea80743c3c90d4a926e37f5099790e2b6acf5fc19c77510",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:36:06.353806+00:00",
        "elapsed_seconds": 1623.09,
        "job": "214745",
        "hostname": "auh7-1b-gpu-282",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "10af6c651dbc",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
        "actual_t5_text": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "10af6c651dbc",
          "arm": "editing",
          "caption": "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
          "caption_sha256": "790782c54c3fea6d88d28f9129501ef060ebc863cd6ead101f7a12563d43e383",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/10af6c651dbc/source-exact81.mp4",
          "source_sha256": "ea86ef53e403f1cc602594cc3623a2fb66fb9b2f65c1461ef2bf62bee82a35fb",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            74,
            2048
          ],
          "feature_sha256": "31d5a8e438020fe75f1d26e7ad419c5e28ba4983c9e49203dd1a52efd9017d75"
        },
        "t5_text_inputs": [
          "The jellyfish pulsates, its bell contracting to reveal a ring-like shape in the blue water. A small, translucent jellyfish with white spots is surrounded by deep blue water. The underwater camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081910,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/10af6c651dbc/source-exact81.mp4",
        "source_sha256": "ea86ef53e403f1cc602594cc3623a2fb66fb9b2f65c1461ef2bf62bee82a35fb",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "d7a3b42e059c8ac6133f96b2fc4664509d504c9f821f45cc24d9d99acb151d44",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:56:21.408682+00:00",
        "elapsed_seconds": 921.01,
        "job": "214733",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "7fa338474c75",
    "name": "Playful selfie",
    "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
    "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
    "outputs": [
      {
        "status": "complete",
        "case_id": "7fa338474c75",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 61,
        "prompt_truncated": false,
        "seed": 2026081900,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_max",
            "sigma_min"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "9f68a732503e5d11d4b94ee86ea61175d555092ffc539b69615faf0e050a083d",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:03:56.015342+00:00",
        "elapsed_seconds": 558.77,
        "job": "214701",
        "hostname": "auh7-1b-gpu-283",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "7fa338474c75",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
        "actual_t5_text": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "7fa338474c75",
          "arm": "t2v",
          "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
          "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            46,
            2048
          ],
          "feature_sha256": "d54fddcf16850d14dc9dfb71b863ba619646a35c90cd4dd2d62419a2adda477a"
        },
        "t5_text_inputs": [
          "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081900,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "0c6b53c4bae5fa1c7275fb71f5197c6312876d3813ae35b9c4db361712d3c65f",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:20:46.292401+00:00",
        "elapsed_seconds": 595.85,
        "job": "214722",
        "hostname": "auh7-1b-gpu-283",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "7fa338474c75",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 100,
        "prompt_truncated": false,
        "seed": 2026081900,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7fa338474c75/source-exact81.mp4",
        "source_sha256": "4278c748fa1fdd54d908c366a781df33d3e4eb1acc1c2b7bd3492659c66a9840",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "sigma_max",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "d80fbfb74a6ab3aed91b258c759a2eb21e37b66c82513742590b0e512e0f49f4",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:36:39.558813+00:00",
        "elapsed_seconds": 1623.02,
        "job": "214746",
        "hostname": "auh7-1b-gpu-313",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "7fa338474c75",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
        "actual_t5_text": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "7fa338474c75",
          "arm": "editing",
          "caption": "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
          "caption_sha256": "f7d22ce2d98ed6adff42d53192e7204016d9035165349de21317c756823ac96e",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7fa338474c75/source-exact81.mp4",
          "source_sha256": "4278c748fa1fdd54d908c366a781df33d3e4eb1acc1c2b7bd3492659c66a9840",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            73,
            2048
          ],
          "feature_sha256": "dc6a8fcf6aace395826a95d45c233eabfd1bbacf9f833e8de912e13129a059d8"
        },
        "t5_text_inputs": [
          "The woman in a red bikini top and straw hat takes a playful selfie with her phone, sticking her tongue out and winking. She is framed in a static medium shot against a uniform green screen background.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081900,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/7fa338474c75/source-exact81.mp4",
        "source_sha256": "4278c748fa1fdd54d908c366a781df33d3e4eb1acc1c2b7bd3492659c66a9840",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "e4267370c4b549bba46b2c14020f9fff2a725e1b4c90379041ab73bbeb59e8be",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:51:53.409740+00:00",
        "elapsed_seconds": 636.88,
        "job": "214734",
        "hostname": "auh7-1b-gpu-282",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "81533c9e56ec",
    "name": "Scarf spin",
    "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
    "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
    "outputs": [
      {
        "status": "complete",
        "case_id": "81533c9e56ec",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 65,
        "prompt_truncated": false,
        "seed": 2026081915,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "sigma_max",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "d7a3869e2f1e3f30b90495f183234d1dcd56b5566c27678ac94669f243f45be8",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:03:06.079836+00:00",
        "elapsed_seconds": 499.76,
        "job": "214702",
        "hostname": "auh7-1b-gpu-312",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "81533c9e56ec",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
        "actual_t5_text": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "81533c9e56ec",
          "arm": "t2v",
          "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
          "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            49,
            2048
          ],
          "feature_sha256": "55500ce71d10d808501849ae5c122f61dbff99b38bd16dd415fb146d599a62c3"
        },
        "t5_text_inputs": [
          "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081915,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "a78f02ecb3aaa875cec8a133397227a526d4ea0e8dadf0a79bb3d7f8478f49e2",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:21:31.826216+00:00",
        "elapsed_seconds": 612.01,
        "job": "214723",
        "hostname": "auh7-1b-gpu-313",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "81533c9e56ec",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 104,
        "prompt_truncated": false,
        "seed": 2026081915,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/81533c9e56ec/source-exact81.mp4",
        "source_sha256": "6daa80d3ac407b01f842ce6fa611b3ec6c421851525f0845779143c4577e0b19",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "shift_terminal",
            "sigma_min",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "6568610950f2753ca3d4c6812018131d53241cb7921236502d6b4d4946380dd9",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:47:28.810955+00:00",
        "elapsed_seconds": 2245.25,
        "job": "214747",
        "hostname": "auh7-1b-gpu-206",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "81533c9e56ec",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
        "actual_t5_text": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "81533c9e56ec",
          "arm": "editing",
          "caption": "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
          "caption_sha256": "f6e77c2c4c9a431ed92369c65484776cb036d47a4d72c6a19e11d2a4d5b09579",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/81533c9e56ec/source-exact81.mp4",
          "source_sha256": "6daa80d3ac407b01f842ce6fa611b3ec6c421851525f0845779143c4577e0b19",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            76,
            2048
          ],
          "feature_sha256": "09cbf7460835b917d1811c9612fb73eb0bd7c7ad17b988a8093c86702c180100"
        },
        "t5_text_inputs": [
          "The woman wearing a green skirt and black shirt gracefully spins in a circle while holding a scarf. Her scarf is red and white. A flower-lined fence and a rustic wooden house form the background. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081915,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/81533c9e56ec/source-exact81.mp4",
        "source_sha256": "6daa80d3ac407b01f842ce6fa611b3ec6c421851525f0845779143c4577e0b19",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "d156e96a7fb7d91ea4a5e0159841362af432c9fed0b20882a8d508796398f671",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:52:22.199956+00:00",
        "elapsed_seconds": 650.56,
        "job": "214735",
        "hostname": "auh7-1b-gpu-313",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "d977ce147d80",
    "name": "Rub eyes then cover face",
    "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
    "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
    "outputs": [
      {
        "status": "complete",
        "case_id": "d977ce147d80",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 70,
        "prompt_truncated": false,
        "seed": 2026081905,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "shift_terminal",
            "sigma_min"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "bad7436ab05bc9d57e503b271ad88b897e1a1ee4db3d8c43c940ce83c37cbf1e",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:04:24.410554+00:00",
        "elapsed_seconds": 578.94,
        "job": "214703",
        "hostname": "auh7-1b-gpu-313",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "d977ce147d80",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
        "actual_t5_text": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "d977ce147d80",
          "arm": "t2v",
          "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
          "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            56,
            2048
          ],
          "feature_sha256": "f578112393aca285a045449d97541a449320571490c0012b73a7d22c73d52bdd"
        },
        "t5_text_inputs": [
          "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081905,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "802cb826e1a39c7a3e2adcb35e2e2288439bc8acfaa86ec6c68dd450b95601f6",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:21:34.897069+00:00",
        "elapsed_seconds": 599.87,
        "job": "214724",
        "hostname": "auh7-1b-gpu-282",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "d977ce147d80",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 109,
        "prompt_truncated": false,
        "seed": 2026081905,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d977ce147d80/source-exact81.mp4",
        "source_sha256": "e2a056e1af423be25a5beb4b75d1145fbacd625e3316a8e64b6031e75739f80d",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "shift_terminal",
            "sigma_max"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "24f7ac9b4d8248228c92995b84173dca81c0bae42f890f507c6fc46f9fae3a43",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:49:26.067248+00:00",
        "elapsed_seconds": 2309.32,
        "job": "214748",
        "hostname": "auh7-1b-gpu-269",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "d977ce147d80",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
        "actual_t5_text": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "d977ce147d80",
          "arm": "editing",
          "caption": "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
          "caption_sha256": "a217f2a0d32d07e58d5c5781d12d401ed7a08f25d9286ea9f0bee5c25677e960",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d977ce147d80/source-exact81.mp4",
          "source_sha256": "e2a056e1af423be25a5beb4b75d1145fbacd625e3316a8e64b6031e75739f80d",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            83,
            2048
          ],
          "feature_sha256": "a9f5554f6eb78289b924250b313712b58c925a9b0599cc70399b9a099117334c"
        },
        "t5_text_inputs": [
          "The man lying on the couch rubs his tired eyes and covers his face with both hands. He has dark skin, dreadlocks, and a gold septum ring. The couch is dark and the room is dimly lit. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081905,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d977ce147d80/source-exact81.mp4",
        "source_sha256": "e2a056e1af423be25a5beb4b75d1145fbacd625e3316a8e64b6031e75739f80d",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "1ecb531ea6b3a35432fabcb94944940f4a199b8b14067578cf2378b5ab32c23d",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:09:38.268251+00:00",
        "elapsed_seconds": 1047.39,
        "job": "214736",
        "hostname": "auh7-1b-gpu-269",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "840b214afead",
    "name": "Place bottle on treadmill",
    "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
    "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
    "outputs": [
      {
        "status": "complete",
        "case_id": "840b214afead",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 71,
        "prompt_truncated": false,
        "seed": 2026081913,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "sigma_min",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "88c0e40f239232c6cbb95be01496886f9100f26023b357bc13dd26715e4155cb",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:49:44.701325+00:00",
        "elapsed_seconds": 545.02,
        "job": "214704",
        "hostname": "auh7-1b-gpu-307",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "840b214afead",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
        "actual_t5_text": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "840b214afead",
          "arm": "t2v",
          "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
          "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            54,
            2048
          ],
          "feature_sha256": "dd48866a02a17042eef8b6cbde060576c10deaf6137ee965388861edfd103d7a"
        },
        "t5_text_inputs": [
          "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081913,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "86baea5251e3c110b691d72b25cfb9405e3039affbbaf8e921c7e9169101b1c2",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:36:13.591878+00:00",
        "elapsed_seconds": 1029.69,
        "job": "214725",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "840b214afead",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 110,
        "prompt_truncated": false,
        "seed": 2026081913,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/840b214afead/source-exact81.mp4",
        "source_sha256": "a6e42a447d7fef26b073878c551a631afd6371987910a332e51e4a9e4dfb4646",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_min",
            "sigma_max",
            "shift_terminal"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "aa4f8096577b9224c04eadfefb1581272b7a1355a9a730939813296ef15d39a2",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:59:20.369231+00:00",
        "elapsed_seconds": 2401.86,
        "job": "214749",
        "hostname": "auh7-1b-gpu-320",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "840b214afead",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
        "actual_t5_text": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "840b214afead",
          "arm": "editing",
          "caption": "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
          "caption_sha256": "fe3b668a66485813f97192ae443c497bc34efcc6edbd10bbdf8af1724af85247",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/840b214afead/source-exact81.mp4",
          "source_sha256": "a6e42a447d7fef26b073878c551a631afd6371987910a332e51e4a9e4dfb4646",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            81,
            2048
          ],
          "feature_sha256": "8d2079d5bd9b6692dfeb7a739b208a4eaf19cf1aca8b431b9a99ec76318349d8"
        },
        "t5_text_inputs": [
          "The woman turns her head to the left and places her water bottle onto the treadmill. She has long reddish-blonde hair and wears a mint green athletic outfit. The modern gym has blue and white striped pillars. The camera is stationary.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081913,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/840b214afead/source-exact81.mp4",
        "source_sha256": "a6e42a447d7fef26b073878c551a631afd6371987910a332e51e4a9e4dfb4646",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "8e7370fc84142be3daa707d6ffc7ff82556f7167a6fe14ed26ce5112d574f625",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:08:46.895702+00:00",
        "elapsed_seconds": 974.76,
        "job": "214737",
        "hostname": "auh7-1b-gpu-206",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  },
  {
    "case_id": "d908552fb691",
    "name": "Bow to clap",
    "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
    "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
    "outputs": [
      {
        "status": "complete",
        "case_id": "d908552fb691",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "t2v",
        "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
        "actual_t5_text": "You are a helpful assistant specialized in text-to-video generation.The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "task_prefix": "You are a helpful assistant specialized in text-to-video generation.",
        "native_reference_binding": "",
        "prompt_rewriting": false,
        "positive_token_count": 60,
        "prompt_truncated": false,
        "seed": 2026081903,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "shift_terminal",
            "sigma_min"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          26,
          54
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "4316ede62030399da548d0b2b136333c622705fe1395b948ab7d60eca68430ce",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:45:46.786299+00:00",
        "elapsed_seconds": 730.83,
        "job": "214705",
        "hostname": "auh7-1b-gpu-206",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "d908552fb691",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "t2v",
        "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
        "actual_t5_text": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "d908552fb691",
          "arm": "t2v",
          "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
          "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
          "source_video_path": null,
          "source_sha256": null,
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            51,
            2048
          ],
          "feature_sha256": "104ba746d40a2909261000fd07d3cefaf8f075beea1e2f6d4224a62c95937b01"
        },
        "t5_text_inputs": [
          "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 1,
        "seed": 2026081903,
        "steps": 40,
        "fps": 25,
        "source_video": null,
        "source_sha256": null,
        "real_target_used": false,
        "visual_latent_shape": null,
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "7458de291881bf7e8eb7909a7dbad8fae1c01726304a6494eb637e4ba845c60b",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T20:32:53.829299+00:00",
        "elapsed_seconds": 603.13,
        "job": "214726",
        "hostname": "auh7-1b-gpu-312",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      },
      {
        "status": "complete",
        "case_id": "d908552fb691",
        "model": "ByteDance/Bernini-R-Diffusers",
        "revision": "de8c4621d3ac75cc33efe3db8deaed2023e9ac8c",
        "arm": "editing",
        "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
        "actual_t5_text": "You are a helpful assistant specialized in video editing with reference.image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "task_prefix": "You are a helpful assistant specialized in video editing with reference.",
        "native_reference_binding": "image0, image1, image2, and image3 are frames sampled from the source video. Preserve the source subject's identity, background, and camera while applying the requested new action. ",
        "prompt_rewriting": false,
        "positive_token_count": 99,
        "prompt_truncated": false,
        "seed": 2026081903,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d908552fb691/source-exact81.mp4",
        "source_sha256": "56e1faa78c02c32d6da71354e8434241c8e9a4c334da4ac8aa4415148b6230bb",
        "effective_scheduler_config": {
          "num_train_timesteps": 1000,
          "beta_start": 0.0001,
          "beta_end": 0.02,
          "beta_schedule": "linear",
          "trained_betas": null,
          "solver_order": 2,
          "prediction_type": "flow_prediction",
          "thresholding": false,
          "dynamic_thresholding_ratio": 0.995,
          "sample_max_value": 1.0,
          "predict_x0": true,
          "solver_type": "bh2",
          "lower_order_final": true,
          "disable_corrector": [],
          "solver_p": null,
          "use_karras_sigmas": false,
          "use_exponential_sigmas": false,
          "use_beta_sigmas": false,
          "use_flow_sigmas": true,
          "flow_shift": 3.0,
          "timestep_spacing": "linspace",
          "steps_offset": 0,
          "final_sigmas_type": "zero",
          "rescale_betas_zero_snr": false,
          "use_dynamic_shifting": false,
          "time_shift_type": "exponential",
          "sigma_min": null,
          "sigma_max": null,
          "shift_terminal": null,
          "_use_default_values": [
            "sigma_max",
            "shift_terminal",
            "sigma_min"
          ],
          "_class_name": "UniPCMultistepScheduler",
          "_diffusers_version": "0.35.0.dev0"
        },
        "source_reference_frames": [
          0,
          27,
          53,
          80
        ],
        "real_target_used": false,
        "expert_parameters": [
          14288491584,
          14288491584
        ],
        "expert_forward_counts": [
          52,
          108
        ],
        "loading_info": [
          {
            "subfolder": "transformer",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          },
          {
            "subfolder": "transformer_2",
            "info": {
              "missing_keys": [],
              "unexpected_keys": [],
              "mismatched_keys": [],
              "error_msgs": []
            }
          }
        ],
        "output": {
          "sha256": "f164b04e01c335a49aca4f94494b87bd5ff2253a61f7d158fa2ddd00ade9967b",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 464,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:59:03.774298+00:00",
        "elapsed_seconds": 2250.01,
        "job": "214750",
        "hostname": "auh7-1b-gpu-221",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "700a4e76177713a6ba2ff7bb92d7976788b646bf153ad7154701ed422ca966d6"
      },
      {
        "status": "complete",
        "case_id": "d908552fb691",
        "model": "Fudan-FUXI/OmniVideo2-A14B",
        "revision": "51160486a5498cce099bde02cbf232cd046ab4a9",
        "arm": "editing",
        "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
        "actual_t5_text": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
        "prompt_rewriting": false,
        "qwen_features": {
          "case_id": "d908552fb691",
          "arm": "editing",
          "caption": "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
          "caption_sha256": "025f04cb7e601915763666a56d60e01f88ed30d6efa85a172c0cf38eff834896",
          "source_video_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d908552fb691/source-exact81.mp4",
          "source_sha256": "56e1faa78c02c32d6da71354e8434241c8e9a4c334da4ac8aa4415148b6230bb",
          "rewriting_enabled": false,
          "autoregressive_generate_forbidden": true,
          "qwen_checkpoint": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
          "feature_shape": [
            78,
            2048
          ],
          "feature_sha256": "114740c8405aa14069531f4ff749cc0da9706f5fe07cf087a02f9e11bbdbc19c"
        },
        "t5_text_inputs": [
          "The woman in a taekwondo uniform stands in profile and claps her hands together in front of her. Her uniform is white with a black collar. The background is black with side lighting, in a static medium shot.",
          "overly vivid colors, overexposed, static, blurry and unclear details, subtitles, text overlays, stylized artwork, painting, illustration, still image, frozen frame, grayish overall tone, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed anatomy, distorted limbs, fused fingers, motionless frame, cluttered background, three legs, walking backward, expression drift, teeth flickering, uneven facial muscles, facial shivering"
        ],
        "positive_t5_context_copies": 2,
        "seed": 2026081903,
        "steps": 40,
        "fps": 25,
        "source_video": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/preprocessed_sources/d908552fb691/source-exact81.mp4",
        "source_sha256": "56e1faa78c02c32d6da71354e8434241c8e9a4c334da4ac8aa4415148b6230bb",
        "real_target_used": false,
        "visual_latent_shape": [
          1,
          16,
          21,
          60,
          104
        ],
        "expert_parameters": [
          14319177792,
          14319177792
        ],
        "expert_forward_counts": [
          34,
          46
        ],
        "strict_checkpoint_load": true,
        "max_context_length": 9216,
        "context_truncation": false,
        "output": {
          "sha256": "aafdce633f1ac4a24120c74a0a75ddb3a4b8a4198e0734ce3643bf8124d8ceb2",
          "avg_frame_rate": "25/1",
          "codec_name": "h264",
          "duration": "3.240000000",
          "height": 480,
          "nb_read_frames": "81",
          "width": 832
        },
        "full_decode_passed": true,
        "completed_utc": "2026-09-23T21:05:24.214802+00:00",
        "elapsed_seconds": 651.09,
        "job": "214738",
        "hostname": "auh7-1b-gpu-307",
        "inputs_sha256": "caa915bc2243c0e21f38532c0b4100e7e4078e575d5d14f54656edc91cd3a535",
        "driver_sha256": "c83cf03c774b3f29f430e9442d6667e5d7d26e7813a836379620c875e83b8295"
      }
    ]
  }
]