{
  "verified": true,
  "num_questions": 30,
  "num_videos": 8,
  "correct": 27,
  "accuracy": 0.9,
  "per_video": {
    "sample_1": {
      "n": 5,
      "correct": 5
    },
    "sample_2": {
      "n": 3,
      "correct": 3
    },
    "sample_3": {
      "n": 5,
      "correct": 4
    },
    "sample_4": {
      "n": 4,
      "correct": 3
    },
    "sample_5": {
      "n": 2,
      "correct": 2
    },
    "sample_6": {
      "n": 5,
      "correct": 4
    },
    "sample_7": {
      "n": 3,
      "correct": 3
    },
    "sample_8": {
      "n": 3,
      "correct": 3
    }
  },
  "wrong_questions": [
    {
      "question_id": "sample_3_a1290_q1",
      "question": "What is the position relationship between the woman in a black dress and the woman in a white outfit?",
      "ground_truth": "A",
      "prediction": "C",
      "options": [
        "A. They are standing side by side.",
        "B. They are standing back to back.",
        "C. The woman in black is in front of the woman in white.",
        "D. The woman in white is holding the trophy."
      ],
      "timestamp_s": 20
    },
    {
      "question_id": "sample_4_a611_q0",
      "question": "What was the score and the position of the teams right now?",
      "ground_truth": "C",
      "prediction": "A",
      "options": [
        "A. 1-0, the team in blue and red is leading.",
        "B. 2-0, the team in white is leading.",
        "C. 2-0, the team in blue and red is leading.",
        "D. 1-1, the teams are tied."
      ],
      "timestamp_s": 64
    },
    {
      "question_id": "sample_6_a1423_q0",
      "question": "What is the player in the black jersey doing just now?",
      "ground_truth": "D",
      "prediction": "A",
      "options": [
        "A. Raising both arms.",
        "B. Moving away from the ball.",
        "C. Running toward the crowd.",
        "D. Bending down to adjust the football."
      ],
      "timestamp_s": 293
    }
  ],
  "mean_inference_s": 0.28449627620478474,
  "median_inference_s": 0.2846074324916117,
  "mean_total_s": 0.946992881258484,
  "sessions": [
    {
      "started_at": "2026-10-24T15:37:23.234904+00:00",
      "dry_run": false,
      "model_load_s": 15.961051500984468,
      "warmup_s": 1.2212338410317898,
      "wall_s": 20.110391080961563,
      "warmup_performed": true
    },
    {
      "started_at": "2026-10-24T15:37:43.812224+00:00",
      "dry_run": false,
      "model_load_s": 8.643092587590218e-05,
      "warmup_s": 0.2823003769153729,
      "wall_s": 28.368568234029226,
      "warmup_performed": true
    }
  ],
  "scope": "manually filtered 30-question engineering subset; not full StreamingBench"
}