{
  "_comment": "Worked example of the per-clip action-annotation contract (annotation.schema.json).",
  "clip_id": "a1b2c3d4e5f_12000_98500",
  "video_id": "a1b2c3d4e5f",
  "transform_version": "a1b2c3d-v1",
  "viewpoint": "head_cam",
  "egocentric_score": 0.93,
  "domain": "cooking",
  "language": "en",
  "duration_s": 86.5,
  "fps": 30,
  "width": 1920,
  "height": 1080,
  "caption": "A person kneads dough on a floured counter, then shapes it into a ball.",
  "asr": [
    {
      "start": 0.4,
      "end": 3.1,
      "text": "now we knead the dough for about ten minutes",
      "words": [
        {
          "w": "now",
          "s": 0.4,
          "e": 0.55
        }
      ]
    }
  ],
  "steps": [
    {
      "step_index": 1,
      "start": 0.0,
      "end": 34.2,
      "summary": "Knead the dough"
    },
    {
      "step_index": 2,
      "start": 34.2,
      "end": 86.5,
      "summary": "Shape into a ball"
    }
  ],
  "segments": [
    {
      "start": 3.2,
      "end": 11.8,
      "step_index": 1,
      "action_verb": "knead",
      "taxonomy": {
        "epic_verb_id": 45,
        "epic_verb": "knead",
        "epic_noun_id": 12,
        "epic_noun": "dough",
        "method": "cosine",
        "sim": 0.91,
        "vocab": "epic",
        "out_of_vocab": false
      },
      "caption": "Two hands press and fold pale dough on a wooden surface.",
      "asr_text": "now we knead the dough for about ten minutes",
      "motion_score": 2.4,
      "egomotion_score": 0.6
    }
  ]
}