frontend/src/videoData.js

const initialVideos = [
  {
    "video_id": "Si_So_abs_ord_SiSo_v1_raw",
    "item_id": "Si_So_abs_ord_SiSo",
    "variant": "1",
    "video_url": "/videos/Si_So_abs_ord_SiSo_v1_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs visible, and both hands initially resting on the knees or thighs. At 1.5 seconds, the person’s right hand forms and clearly holds a thumbs-up pose, with the fist closed and the thumb extended upward. At 3.5 seconds, the person’s right hand strikes the top of the right thigh, making visible contact and producing a sharp slap sound exactly at impact. The thumbs-up is completed before the thigh slap begins, and the two events do not overlap. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.5s; thigh slap at 3.5s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 22,
      "item_id": "Si_So_abs_ord_SiSo",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 64,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.5s; thigh slap at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_ord_SiSo_v2_raw",
    "item_id": "Si_So_abs_ord_SiSo",
    "variant": "2",
    "video_url": "/videos/Si_So_abs_ord_SiSo_v2_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs visible, and both hands initially resting on the knees or thighs. At 1.5 seconds, the person’s right hand forms and clearly holds a thumbs-up pose, with the fist closed and the thumb extended upward. At 3.5 seconds, the person’s right hand strikes the top of the right thigh, making visible contact and producing a sharp slap sound exactly at impact. The thumbs-up is completed before the thigh slap begins, and the two events do not overlap. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.5s; thigh slap at 3.5s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 22,
      "item_id": "Si_So_abs_ord_SiSo",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 65,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.5s; thigh slap at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_ord_SiSo_v3_raw",
    "item_id": "Si_So_abs_ord_SiSo",
    "variant": "3",
    "video_url": "/videos/Si_So_abs_ord_SiSo_v3_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs visible, and both hands initially resting on the knees or thighs. At 1.5 seconds, the person’s right hand forms and clearly holds a thumbs-up pose, with the fist closed and the thumb extended upward. At 3.5 seconds, the person’s right hand strikes the top of the right thigh, making visible contact and producing a sharp slap sound exactly at impact. The thumbs-up is completed before the thigh slap begins, and the two events do not overlap. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.5s; thigh slap at 3.5s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 22,
      "item_id": "Si_So_abs_ord_SiSo",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 66,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.5s; thigh slap at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_ord_SoSi_v1_raw",
    "item_id": "Si_So_abs_ord_SoSi",
    "variant": "1",
    "video_url": "/videos/Si_So_abs_ord_SoSi_v1_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.5 seconds, the person’s right hand strikes the top of the right thigh with visible contact and a sharp slap sound at the moment of impact. At 3.5 seconds, the person forms and holds a clear right-hand thumbs-up pose, with the thumb extended upward and the fist closed, without raising the hand as a separate target action. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.5s; thumbs-up at 3.5s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 23,
      "item_id": "Si_So_abs_ord_SoSi",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 65,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.5s; thumbs-up at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_ord_SoSi_v2_raw",
    "item_id": "Si_So_abs_ord_SoSi",
    "variant": "2",
    "video_url": "/videos/Si_So_abs_ord_SoSi_v2_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.5 seconds, the person’s right hand strikes the top of the right thigh with visible contact and a sharp slap sound at the moment of impact. At 3.5 seconds, the person forms and holds a clear right-hand thumbs-up pose, with the thumb extended upward and the fist closed, without raising the hand as a separate target action. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.5s; thumbs-up at 3.5s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 23,
      "item_id": "Si_So_abs_ord_SoSi",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 66,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.5s; thumbs-up at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_ord_SoSi_v3_raw",
    "item_id": "Si_So_abs_ord_SoSi",
    "variant": "3",
    "video_url": "/videos/Si_So_abs_ord_SoSi_v3_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.5 seconds, the person’s right hand strikes the top of the right thigh with visible contact and a sharp slap sound at the moment of impact. At 3.5 seconds, the person forms and holds a clear right-hand thumbs-up pose, with the thumb extended upward and the fist closed, without raising the hand as a separate target action. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.5s; thumbs-up at 3.5s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 23,
      "item_id": "Si_So_abs_ord_SoSi",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 67,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.5s; thumbs-up at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_sync_cnt_v1_raw",
    "item_id": "Si_So_abs_sync_cnt",
    "variant": "1",
    "video_url": "/videos/Si_So_abs_sync_cnt_v1_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible, and both hands initially resting on the knees or thighs. At 1.5 seconds, the person’s right hand forms a clear thumbs-up pose while the same right hand simultaneously strikes the top of the right thigh, making visible contact and a sharp slap sound at the moment of impact. At 3.5 seconds, the same combined action happens again once more: the right hand again shows the thumbs-up pose while contacting the right thigh with another sharp slap sound. The thumbs-up is a held pose, not a separate raising motion, and the slap sound occurs only at impact. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap at 1.5s; thumbs-up + thigh slap at 3.5s"
      },
      {
        "type": "Count",
        "text": "2 synchronized event groups"
      }
    ],
    "metadata": {
      "index": 21,
      "item_id": "Si_So_abs_sync_cnt",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 63,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "sync_count",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "Si_action",
                "So_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "Si_action",
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "sync_count_relation",
          "title": "Sync count",
          "description": "thumbs-up + thigh slap at 1.5s; thumbs-up + thigh slap at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "synchronized_event_group_count",
          "title": "Exactly 2 synchronized event groups",
          "description": "Count the number of synchronized event groups requested by the prompt."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_sync_cnt_v2_raw",
    "item_id": "Si_So_abs_sync_cnt",
    "variant": "2",
    "video_url": "/videos/Si_So_abs_sync_cnt_v2_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible, and both hands initially resting on the knees or thighs. At 1.5 seconds, the person’s right hand forms a clear thumbs-up pose while the same right hand simultaneously strikes the top of the right thigh, making visible contact and a sharp slap sound at the moment of impact. At 3.5 seconds, the same combined action happens again once more: the right hand again shows the thumbs-up pose while contacting the right thigh with another sharp slap sound. The thumbs-up is a held pose, not a separate raising motion, and the slap sound occurs only at impact. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap at 1.5s; thumbs-up + thigh slap at 3.5s"
      },
      {
        "type": "Count",
        "text": "2 synchronized event groups"
      }
    ],
    "metadata": {
      "index": 21,
      "item_id": "Si_So_abs_sync_cnt",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 64,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "sync_count",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "Si_action",
                "So_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "Si_action",
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "sync_count_relation",
          "title": "Sync count",
          "description": "thumbs-up + thigh slap at 1.5s; thumbs-up + thigh slap at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "synchronized_event_group_count",
          "title": "Exactly 2 synchronized event groups",
          "description": "Count the number of synchronized event groups requested by the prompt."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_sync_cnt_v3_raw",
    "item_id": "Si_So_abs_sync_cnt",
    "variant": "3",
    "video_url": "/videos/Si_So_abs_sync_cnt_v3_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible, and both hands initially resting on the knees or thighs. At 1.5 seconds, the person’s right hand forms a clear thumbs-up pose while the same right hand simultaneously strikes the top of the right thigh, making visible contact and a sharp slap sound at the moment of impact. At 3.5 seconds, the same combined action happens again once more: the right hand again shows the thumbs-up pose while contacting the right thigh with another sharp slap sound. The thumbs-up is a held pose, not a separate raising motion, and the slap sound occurs only at impact. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap at 1.5s; thumbs-up + thigh slap at 3.5s"
      },
      {
        "type": "Count",
        "text": "2 synchronized event groups"
      }
    ],
    "metadata": {
      "index": 21,
      "item_id": "Si_So_abs_sync_cnt",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 65,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "sync_count",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.5,
              "events": [
                "Si_action",
                "So_action"
              ]
            },
            {
              "time_sec": 3.5,
              "events": [
                "Si_action",
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "sync_count_relation",
          "title": "Sync count",
          "description": "thumbs-up + thigh slap at 1.5s; thumbs-up + thigh slap at 3.5s"
        }
      ],
      "temporal_count": [
        {
          "id": "synchronized_event_group_count",
          "title": "Exactly 2 synchronized event groups",
          "description": "Count the number of synchronized event groups requested by the prompt."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_sync_v1_raw",
    "item_id": "Si_So_abs_sync",
    "variant": "1",
    "video_url": "/videos/Si_So_abs_sync_v1_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs stay visible. At 2.0 seconds, the person’s right hand is held in a clear thumbs-up pose while the same right hand strikes the top of the right thigh at the same moment, with visible contact and a sharp slap sound exactly at impact. The thumbs-up remains clearly recognizable during the contact moment, not as a separate hand-raising motion. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap at 2.0s"
      },
      {
        "type": "Count",
        "text": "1 synchronized event group"
      }
    ],
    "metadata": {
      "index": 20,
      "item_id": "Si_So_abs_sync",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 62,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "synchronization",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 2.0,
              "events": [
                "Si_action",
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "synchronization_relation",
          "title": "Synchronization",
          "description": "thumbs-up + thigh slap at 2.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "event_group_count",
          "title": "Exactly 1 synchronized event group",
          "description": "The synchronized event group occurs exactly once."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_sync_v2_raw",
    "item_id": "Si_So_abs_sync",
    "variant": "2",
    "video_url": "/videos/Si_So_abs_sync_v2_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs stay visible. At 2.0 seconds, the person’s right hand is held in a clear thumbs-up pose while the same right hand strikes the top of the right thigh at the same moment, with visible contact and a sharp slap sound exactly at impact. The thumbs-up remains clearly recognizable during the contact moment, not as a separate hand-raising motion. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap at 2.0s"
      },
      {
        "type": "Count",
        "text": "1 synchronized event group"
      }
    ],
    "metadata": {
      "index": 20,
      "item_id": "Si_So_abs_sync",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 63,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "synchronization",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 2.0,
              "events": [
                "Si_action",
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "synchronization_relation",
          "title": "Synchronization",
          "description": "thumbs-up + thigh slap at 2.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "event_group_count",
          "title": "Exactly 1 synchronized event group",
          "description": "The synchronized event group occurs exactly once."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_abs_sync_v3_raw",
    "item_id": "Si_So_abs_sync",
    "variant": "3",
    "video_url": "/videos/Si_So_abs_sync_v3_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs stay visible. At 2.0 seconds, the person’s right hand is held in a clear thumbs-up pose while the same right hand strikes the top of the right thigh at the same moment, with visible contact and a sharp slap sound exactly at impact. The thumbs-up remains clearly recognizable during the contact moment, not as a separate hand-raising motion. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap at 2.0s"
      },
      {
        "type": "Count",
        "text": "1 synchronized event group"
      }
    ],
    "metadata": {
      "index": 20,
      "item_id": "Si_So_abs_sync",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 64,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "synchronization",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 2.0,
              "events": [
                "Si_action",
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "synchronization_relation",
          "title": "Synchronization",
          "description": "thumbs-up + thigh slap at 2.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "event_group_count",
          "title": "Exactly 1 synchronized event group",
          "description": "The synchronized event group occurs exactly once."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_ord_SoSi_v1_raw",
    "item_id": "Si_So_rel_ord_SoSi",
    "variant": "1",
    "video_url": "/videos/Si_So_rel_ord_SoSi_v1_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person’s right hand strikes the top of the right thigh once, making visible contact and a sharp slap sound at the moment of impact. After that action is completed, the person holds a clear right-hand thumbs-up pose, with the fist closed and the thumb extended upward. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap before thumbs-up"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 19,
      "item_id": "Si_So_rel_ord_SoSi",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 61,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "relative",
        "value": {
          "sequence": [
            "So_action",
            "Si_action"
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap before thumbs-up"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_ord_SoSi_v2_raw",
    "item_id": "Si_So_rel_ord_SoSi",
    "variant": "2",
    "video_url": "/videos/Si_So_rel_ord_SoSi_v2_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person’s right hand strikes the top of the right thigh once, making visible contact and a sharp slap sound at the moment of impact. After that action is completed, the person holds a clear right-hand thumbs-up pose, with the fist closed and the thumb extended upward. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap before thumbs-up"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 19,
      "item_id": "Si_So_rel_ord_SoSi",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 62,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "relative",
        "value": {
          "sequence": [
            "So_action",
            "Si_action"
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap before thumbs-up"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_ord_SoSi_v3_raw",
    "item_id": "Si_So_rel_ord_SoSi",
    "variant": "3",
    "video_url": "/videos/Si_So_rel_ord_SoSi_v3_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person’s right hand strikes the top of the right thigh once, making visible contact and a sharp slap sound at the moment of impact. After that action is completed, the person holds a clear right-hand thumbs-up pose, with the fist closed and the thumb extended upward. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap before thumbs-up"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 19,
      "item_id": "Si_So_rel_ord_SoSi",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 63,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "relative",
        "value": {
          "sequence": [
            "So_action",
            "Si_action"
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap before thumbs-up"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_sync_cnt_v1_raw",
    "item_id": "Si_So_rel_sync_cnt",
    "variant": "1",
    "video_url": "/videos/Si_So_rel_sync_cnt_v1_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera with full face, mouth, upper body, both hands, and thighs clearly visible, and both hands start resting on the knees or thighs. The person’s right hand forms a clear thumbs-up pose while, at the same moment, the same right hand strikes the top of the right thigh, making visible contact and producing a sharp slap sound. This synchronized pair of actions happens exactly two times, with a brief reset between them so the right hand returns to a ready position before the second repetition. The thumbs-up remains clearly recognizable as a closed fist with the thumb extended upward during each synchronized moment, and no other target action occurs. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap"
      },
      {
        "type": "Count",
        "text": "2 synchronized event groups"
      }
    ],
    "metadata": {
      "index": 17,
      "item_id": "Si_So_rel_sync_cnt",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 59,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "sync_count",
        "timing_type": "relative",
        "value": {
          "events": [
            "Si_action",
            "So_action"
          ],
          "count": 2
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "sync_count_relation",
          "title": "Sync count",
          "description": "thumbs-up + thigh slap"
        }
      ],
      "temporal_count": [
        {
          "id": "synchronized_event_group_count",
          "title": "Exactly 2 synchronized event groups",
          "description": "Count the number of synchronized event groups requested by the prompt."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_sync_cnt_v2_raw",
    "item_id": "Si_So_rel_sync_cnt",
    "variant": "2",
    "video_url": "/videos/Si_So_rel_sync_cnt_v2_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera with full face, mouth, upper body, both hands, and thighs clearly visible, and both hands start resting on the knees or thighs. The person’s right hand forms a clear thumbs-up pose while, at the same moment, the same right hand strikes the top of the right thigh, making visible contact and producing a sharp slap sound. This synchronized pair of actions happens exactly two times, with a brief reset between them so the right hand returns to a ready position before the second repetition. The thumbs-up remains clearly recognizable as a closed fist with the thumb extended upward during each synchronized moment, and no other target action occurs. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap"
      },
      {
        "type": "Count",
        "text": "2 synchronized event groups"
      }
    ],
    "metadata": {
      "index": 17,
      "item_id": "Si_So_rel_sync_cnt",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 60,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "sync_count",
        "timing_type": "relative",
        "value": {
          "events": [
            "Si_action",
            "So_action"
          ],
          "count": 2
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "sync_count_relation",
          "title": "Sync count",
          "description": "thumbs-up + thigh slap"
        }
      ],
      "temporal_count": [
        {
          "id": "synchronized_event_group_count",
          "title": "Exactly 2 synchronized event groups",
          "description": "Count the number of synchronized event groups requested by the prompt."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_sync_cnt_v3_raw",
    "item_id": "Si_So_rel_sync_cnt",
    "variant": "3",
    "video_url": "/videos/Si_So_rel_sync_cnt_v3_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera with full face, mouth, upper body, both hands, and thighs clearly visible, and both hands start resting on the knees or thighs. The person’s right hand forms a clear thumbs-up pose while, at the same moment, the same right hand strikes the top of the right thigh, making visible contact and producing a sharp slap sound. This synchronized pair of actions happens exactly two times, with a brief reset between them so the right hand returns to a ready position before the second repetition. The thumbs-up remains clearly recognizable as a closed fist with the thumb extended upward during each synchronized moment, and no other target action occurs. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap"
      },
      {
        "type": "Count",
        "text": "2 synchronized event groups"
      }
    ],
    "metadata": {
      "index": 17,
      "item_id": "Si_So_rel_sync_cnt",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 61,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "sync_count",
        "timing_type": "relative",
        "value": {
          "events": [
            "Si_action",
            "So_action"
          ],
          "count": 2
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "sync_count_relation",
          "title": "Sync count",
          "description": "thumbs-up + thigh slap"
        }
      ],
      "temporal_count": [
        {
          "id": "synchronized_event_group_count",
          "title": "Exactly 2 synchronized event groups",
          "description": "Count the number of synchronized event groups requested by the prompt."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_sync_v1_raw",
    "item_id": "Si_So_rel_sync",
    "variant": "1",
    "video_url": "/videos/Si_So_rel_sync_v1_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs clearly visible. At one moment, the person’s right hand is held in a clear thumbs-up pose while the same right hand simultaneously strikes the top of the right thigh, with visible contact and a sharp slap sound exactly at impact. The thumbs-up is the pose itself, not a separate lifting motion, and the synchronized thumb pose and thigh slap happen together as one event. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap"
      },
      {
        "type": "Count",
        "text": "1 synchronized event group"
      }
    ],
    "metadata": {
      "index": 16,
      "item_id": "Si_So_rel_sync",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 58,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "synchronization",
        "timing_type": "relative",
        "value": {
          "events": [
            "Si_action",
            "So_action"
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "synchronization_relation",
          "title": "Synchronization",
          "description": "thumbs-up + thigh slap"
        }
      ],
      "temporal_count": [
        {
          "id": "event_group_count",
          "title": "Exactly 1 synchronized event group",
          "description": "The synchronized event group occurs exactly once."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_sync_v2_raw",
    "item_id": "Si_So_rel_sync",
    "variant": "2",
    "video_url": "/videos/Si_So_rel_sync_v2_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs clearly visible. At one moment, the person’s right hand is held in a clear thumbs-up pose while the same right hand simultaneously strikes the top of the right thigh, with visible contact and a sharp slap sound exactly at impact. The thumbs-up is the pose itself, not a separate lifting motion, and the synchronized thumb pose and thigh slap happen together as one event. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap"
      },
      {
        "type": "Count",
        "text": "1 synchronized event group"
      }
    ],
    "metadata": {
      "index": 16,
      "item_id": "Si_So_rel_sync",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 59,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "synchronization",
        "timing_type": "relative",
        "value": {
          "events": [
            "Si_action",
            "So_action"
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "synchronization_relation",
          "title": "Synchronization",
          "description": "thumbs-up + thigh slap"
        }
      ],
      "temporal_count": [
        {
          "id": "event_group_count",
          "title": "Exactly 1 synchronized event group",
          "description": "The synchronized event group occurs exactly once."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Si_So_rel_sync_v3_raw",
    "item_id": "Si_So_rel_sync",
    "variant": "3",
    "video_url": "/videos/Si_So_rel_sync_v3_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs clearly visible. At one moment, the person’s right hand is held in a clear thumbs-up pose while the same right hand simultaneously strikes the top of the right thigh, with visible contact and a sharp slap sound exactly at impact. The thumbs-up is the pose itself, not a separate lifting motion, and the synchronized thumb pose and thigh slap happen together as one event. After the final event, no new target action occurs.",
    "events": [
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "synchronization: thumbs-up + thigh slap"
      },
      {
        "type": "Count",
        "text": "1 synchronized event group"
      }
    ],
    "metadata": {
      "index": 16,
      "item_id": "Si_So_rel_sync",
      "category": "Si_So",
      "label": "thumbs_up_slapping_the_thigh",
      "seed": 60,
      "modality_combination": "Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "synchronization",
        "timing_type": "relative",
        "value": {
          "events": [
            "Si_action",
            "So_action"
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "synchronization_relation",
          "title": "Synchronization",
          "description": "thumbs-up + thigh slap"
        }
      ],
      "temporal_count": [
        {
          "id": "event_group_count",
          "title": "Exactly 1 synchronized event group",
          "description": "The synchronized event group occurs exactly once."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SiSoSp_v1_raw",
    "item_id": "Sp_Si_So_abs_ord_SiSoSp",
    "variant": "1",
    "video_url": "/videos/Sp_Si_So_abs_ord_SiSoSp_v1_raw.mp4",
    "prompt": "A single seated person faces the camera in a plain indoor room, shown in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose with the thumb extended upward. At 2.5 seconds, the right hand strikes the top of the right thigh, making visible contact and a sharp slap sound. At 4.0 seconds, the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.0s; thigh slap at 2.5s; speech at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 thigh slap event(s), 1 speech event(s)"
      }
    ],
    "metadata": {
      "index": 37,
      "item_id": "Sp_Si_So_abs_ord_SiSoSp",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 79,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Sp"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.0s; thigh slap at 2.5s; speech at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SiSoSp_v2_raw",
    "item_id": "Sp_Si_So_abs_ord_SiSoSp",
    "variant": "2",
    "video_url": "/videos/Sp_Si_So_abs_ord_SiSoSp_v2_raw.mp4",
    "prompt": "A single seated person faces the camera in a plain indoor room, shown in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose with the thumb extended upward. At 2.5 seconds, the right hand strikes the top of the right thigh, making visible contact and a sharp slap sound. At 4.0 seconds, the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.0s; thigh slap at 2.5s; speech at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 thigh slap event(s), 1 speech event(s)"
      }
    ],
    "metadata": {
      "index": 37,
      "item_id": "Sp_Si_So_abs_ord_SiSoSp",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 80,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Sp"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.0s; thigh slap at 2.5s; speech at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SiSoSp_v3_raw",
    "item_id": "Sp_Si_So_abs_ord_SiSoSp",
    "variant": "3",
    "video_url": "/videos/Sp_Si_So_abs_ord_SiSoSp_v3_raw.mp4",
    "prompt": "A single seated person faces the camera in a plain indoor room, shown in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose with the thumb extended upward. At 2.5 seconds, the right hand strikes the top of the right thigh, making visible contact and a sharp slap sound. At 4.0 seconds, the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.0s; thigh slap at 2.5s; speech at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 thigh slap event(s), 1 speech event(s)"
      }
    ],
    "metadata": {
      "index": 37,
      "item_id": "Sp_Si_So_abs_ord_SiSoSp",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 81,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Sp"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.0s; thigh slap at 2.5s; speech at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SiSpSo_v1_raw",
    "item_id": "Sp_Si_So_abs_ord_SiSpSo",
    "variant": "1",
    "video_url": "/videos/Sp_Si_So_abs_ord_SiSpSo_v1_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose. At 2.5 seconds, the person clearly says the single word “help” and no extra words. At 4.0 seconds, the person strikes the top of the right thigh with the right hand, making visible contact and a sharp slap sound exactly at impact. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.0s; speech at 2.5s; thigh slap at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 speech event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 36,
      "item_id": "Sp_Si_So_abs_ord_SiSpSo",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 78,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.0s; speech at 2.5s; thigh slap at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SiSpSo_v2_raw",
    "item_id": "Sp_Si_So_abs_ord_SiSpSo",
    "variant": "2",
    "video_url": "/videos/Sp_Si_So_abs_ord_SiSpSo_v2_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose. At 2.5 seconds, the person clearly says the single word “help” and no extra words. At 4.0 seconds, the person strikes the top of the right thigh with the right hand, making visible contact and a sharp slap sound exactly at impact. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.0s; speech at 2.5s; thigh slap at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 speech event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 36,
      "item_id": "Sp_Si_So_abs_ord_SiSpSo",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 79,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.0s; speech at 2.5s; thigh slap at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SiSpSo_v3_raw",
    "item_id": "Sp_Si_So_abs_ord_SiSpSo",
    "variant": "3",
    "video_url": "/videos/Sp_Si_So_abs_ord_SiSpSo_v3_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose. At 2.5 seconds, the person clearly says the single word “help” and no extra words. At 4.0 seconds, the person strikes the top of the right thigh with the right hand, making visible contact and a sharp slap sound exactly at impact. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thumbs-up at 1.0s; speech at 2.5s; thigh slap at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thumbs-up event(s), 1 speech event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 36,
      "item_id": "Sp_Si_So_abs_ord_SiSpSo",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 80,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thumbs-up at 1.0s; speech at 2.5s; thigh slap at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SoSiSp_v1_raw",
    "item_id": "Sp_Si_So_abs_ord_SoSiSp",
    "variant": "1",
    "video_url": "/videos/Sp_Si_So_abs_ord_SoSiSp_v1_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and both thighs visible, and both hands initially resting on the knees or thighs. At 1.0 seconds, the person’s right hand strikes the top of the right thigh once, making visible contact and producing a sharp slap sound. After that action ends, at 2.5 seconds the person forms and holds a clear right-hand thumbs-up pose with the thumb extended upward. After that pose is shown, at 4.0 seconds the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.0s; thumbs-up at 2.5s; speech at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s), 1 speech event(s)"
      }
    ],
    "metadata": {
      "index": 39,
      "item_id": "Sp_Si_So_abs_ord_SoSiSp",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 81,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Sp"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.0s; thumbs-up at 2.5s; speech at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SoSiSp_v2_raw",
    "item_id": "Sp_Si_So_abs_ord_SoSiSp",
    "variant": "2",
    "video_url": "/videos/Sp_Si_So_abs_ord_SoSiSp_v2_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and both thighs visible, and both hands initially resting on the knees or thighs. At 1.0 seconds, the person’s right hand strikes the top of the right thigh once, making visible contact and producing a sharp slap sound. After that action ends, at 2.5 seconds the person forms and holds a clear right-hand thumbs-up pose with the thumb extended upward. After that pose is shown, at 4.0 seconds the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.0s; thumbs-up at 2.5s; speech at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s), 1 speech event(s)"
      }
    ],
    "metadata": {
      "index": 39,
      "item_id": "Sp_Si_So_abs_ord_SoSiSp",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 82,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Sp"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.0s; thumbs-up at 2.5s; speech at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SoSiSp_v3_raw",
    "item_id": "Sp_Si_So_abs_ord_SoSiSp",
    "variant": "3",
    "video_url": "/videos/Sp_Si_So_abs_ord_SoSiSp_v3_raw.mp4",
    "prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and both thighs visible, and both hands initially resting on the knees or thighs. At 1.0 seconds, the person’s right hand strikes the top of the right thigh once, making visible contact and producing a sharp slap sound. After that action ends, at 2.5 seconds the person forms and holds a clear right-hand thumbs-up pose with the thumb extended upward. After that pose is shown, at 4.0 seconds the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.0s; thumbs-up at 2.5s; speech at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 thumbs-up event(s), 1 speech event(s)"
      }
    ],
    "metadata": {
      "index": 39,
      "item_id": "Sp_Si_So_abs_ord_SoSiSp",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 83,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Sp"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.0s; thumbs-up at 2.5s; speech at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SoSpSi_v1_raw",
    "item_id": "Sp_Si_So_abs_ord_SoSpSi",
    "variant": "1",
    "video_url": "/videos/Sp_Si_So_abs_ord_SoSpSi_v1_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible, and both hands resting on the knees or thighs at the start. At 1.0 seconds, the person’s right hand strikes the top of the right thigh, making visible contact and producing one sharp slap sound. At 2.5 seconds, the person clearly says “help” and nothing else. At 4.0 seconds, the person forms and holds a clear thumbs-up with the right hand, with the thumb extended upward and the fist closed. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.0s; speech at 2.5s; thumbs-up at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 speech event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 38,
      "item_id": "Sp_Si_So_abs_ord_SoSpSi",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 80,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.0s; speech at 2.5s; thumbs-up at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SoSpSi_v2_raw",
    "item_id": "Sp_Si_So_abs_ord_SoSpSi",
    "variant": "2",
    "video_url": "/videos/Sp_Si_So_abs_ord_SoSpSi_v2_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible, and both hands resting on the knees or thighs at the start. At 1.0 seconds, the person’s right hand strikes the top of the right thigh, making visible contact and producing one sharp slap sound. At 2.5 seconds, the person clearly says “help” and nothing else. At 4.0 seconds, the person forms and holds a clear thumbs-up with the right hand, with the thumb extended upward and the fist closed. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.0s; speech at 2.5s; thumbs-up at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 speech event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 38,
      "item_id": "Sp_Si_So_abs_ord_SoSpSi",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 81,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.0s; speech at 2.5s; thumbs-up at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SoSpSi_v3_raw",
    "item_id": "Sp_Si_So_abs_ord_SoSpSi",
    "variant": "3",
    "video_url": "/videos/Sp_Si_So_abs_ord_SoSpSi_v3_raw.mp4",
    "prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible, and both hands resting on the knees or thighs at the start. At 1.0 seconds, the person’s right hand strikes the top of the right thigh, making visible contact and producing one sharp slap sound. At 2.5 seconds, the person clearly says “help” and nothing else. At 4.0 seconds, the person forms and holds a clear thumbs-up with the right hand, with the thumb extended upward and the fist closed. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: thigh slap at 1.0s; speech at 2.5s; thumbs-up at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 thigh slap event(s), 1 speech event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 38,
      "item_id": "Sp_Si_So_abs_ord_SoSpSi",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 82,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "thigh slap at 1.0s; speech at 2.5s; thumbs-up at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SpSiSo_v1_raw",
    "item_id": "Sp_Si_So_abs_ord_SpSiSo",
    "variant": "1",
    "video_url": "/videos/Sp_Si_So_abs_ord_SpSiSo_v1_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair, with the full face, mouth, upper body, both hands, and thighs clearly visible, and both hands initially resting on the knees or thighs. At 1.0 seconds, the person clearly says the single word “help” and nothing else is spoken. At 2.5 seconds, the person’s right hand forms and holds a clear thumbs-up pose, with the thumb extended upward and the fist closed, without needing a separate raising motion. At 4.0 seconds, the person uses the right hand to slap the top of the right thigh, making visible contact and producing a sharp slap sound at the instant of impact. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: speech at 1.0s; thumbs-up at 2.5s; thigh slap at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 speech event(s), 1 thumbs-up event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 34,
      "item_id": "Sp_Si_So_abs_ord_SpSiSo",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 76,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "speech at 1.0s; thumbs-up at 2.5s; thigh slap at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SpSiSo_v2_raw",
    "item_id": "Sp_Si_So_abs_ord_SpSiSo",
    "variant": "2",
    "video_url": "/videos/Sp_Si_So_abs_ord_SpSiSo_v2_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair, with the full face, mouth, upper body, both hands, and thighs clearly visible, and both hands initially resting on the knees or thighs. At 1.0 seconds, the person clearly says the single word “help” and nothing else is spoken. At 2.5 seconds, the person’s right hand forms and holds a clear thumbs-up pose, with the thumb extended upward and the fist closed, without needing a separate raising motion. At 4.0 seconds, the person uses the right hand to slap the top of the right thigh, making visible contact and producing a sharp slap sound at the instant of impact. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: speech at 1.0s; thumbs-up at 2.5s; thigh slap at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 speech event(s), 1 thumbs-up event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 34,
      "item_id": "Sp_Si_So_abs_ord_SpSiSo",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 77,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "speech at 1.0s; thumbs-up at 2.5s; thigh slap at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SpSiSo_v3_raw",
    "item_id": "Sp_Si_So_abs_ord_SpSiSo",
    "variant": "3",
    "video_url": "/videos/Sp_Si_So_abs_ord_SpSiSo_v3_raw.mp4",
    "prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair, with the full face, mouth, upper body, both hands, and thighs clearly visible, and both hands initially resting on the knees or thighs. At 1.0 seconds, the person clearly says the single word “help” and nothing else is spoken. At 2.5 seconds, the person’s right hand forms and holds a clear thumbs-up pose, with the thumb extended upward and the fist closed, without needing a separate raising motion. At 4.0 seconds, the person uses the right hand to slap the top of the right thigh, making visible contact and producing a sharp slap sound at the instant of impact. After the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: speech at 1.0s; thumbs-up at 2.5s; thigh slap at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 speech event(s), 1 thumbs-up event(s), 1 thigh slap event(s)"
      }
    ],
    "metadata": {
      "index": 34,
      "item_id": "Sp_Si_So_abs_ord_SpSiSo",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 78,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "Si_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "So_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "speech at 1.0s; thumbs-up at 2.5s; thigh slap at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SpSoSi_v1_raw",
    "item_id": "Sp_Si_So_abs_ord_SpSoSi",
    "variant": "1",
    "video_url": "/videos/Sp_Si_So_abs_ord_SpSoSi_v1_raw.mp4",
    "prompt": "A static medium shot in a plain indoor room shows one seated person facing the camera, with the full face, mouth, upper body, both hands, and thighs clearly visible; they begin seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person clearly says the single word “help” and no other words. At 2.5 seconds, the person’s right hand strikes the top of their right thigh, making visible contact and producing a sharp slap sound exactly at impact. At 4.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose, with the thumb extended upward and the fist closed. After each event, the earlier action is completed before the next begins, and after the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: speech at 1.0s; thigh slap at 2.5s; thumbs-up at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 speech event(s), 1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 35,
      "item_id": "Sp_Si_So_abs_ord_SpSoSi",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 77,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "speech at 1.0s; thigh slap at 2.5s; thumbs-up at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SpSoSi_v2_raw",
    "item_id": "Sp_Si_So_abs_ord_SpSoSi",
    "variant": "2",
    "video_url": "/videos/Sp_Si_So_abs_ord_SpSoSi_v2_raw.mp4",
    "prompt": "A static medium shot in a plain indoor room shows one seated person facing the camera, with the full face, mouth, upper body, both hands, and thighs clearly visible; they begin seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person clearly says the single word “help” and no other words. At 2.5 seconds, the person’s right hand strikes the top of their right thigh, making visible contact and producing a sharp slap sound exactly at impact. At 4.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose, with the thumb extended upward and the fist closed. After each event, the earlier action is completed before the next begins, and after the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: speech at 1.0s; thigh slap at 2.5s; thumbs-up at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 speech event(s), 1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 35,
      "item_id": "Sp_Si_So_abs_ord_SpSoSi",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 78,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "speech at 1.0s; thigh slap at 2.5s; thumbs-up at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  },
  {
    "video_id": "Sp_Si_So_abs_ord_SpSoSi_v3_raw",
    "item_id": "Sp_Si_So_abs_ord_SpSoSi",
    "variant": "3",
    "video_url": "/videos/Sp_Si_So_abs_ord_SpSoSi_v3_raw.mp4",
    "prompt": "A static medium shot in a plain indoor room shows one seated person facing the camera, with the full face, mouth, upper body, both hands, and thighs clearly visible; they begin seated on a chair with both hands resting on the knees or thighs. At 1.0 seconds, the person clearly says the single word “help” and no other words. At 2.5 seconds, the person’s right hand strikes the top of their right thigh, making visible contact and producing a sharp slap sound exactly at impact. At 4.0 seconds, the person’s right hand forms and holds a clear thumbs-up pose, with the thumb extended upward and the fist closed. After each event, the earlier action is completed before the next begins, and after the final event, no new target action occurs.",
    "events": [
      "Sp: The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required.",
      "Si_action: The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion.",
      "So_action: The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
    ],
    "constraints": [
      {
        "type": "Relation",
        "text": "order: speech at 1.0s; thigh slap at 2.5s; thumbs-up at 4.0s"
      },
      {
        "type": "Count",
        "text": "1 speech event(s), 1 thigh slap event(s), 1 thumbs-up event(s)"
      }
    ],
    "metadata": {
      "index": 35,
      "item_id": "Sp_Si_So_abs_ord_SpSoSi",
      "category": "Sp_Si_So",
      "label": "help_thumbs_up_slapping_the_thigh",
      "seed": 79,
      "modality_combination": "Speech + Action (Si) + Action (So)",
      "scene_hint": "plain indoor room",
      "camera_hint": "static medium shot"
    },
    "source_details": {
      "subjects": [
        {
          "id": "person_A",
          "description": "one seated person facing the camera",
          "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
          "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
        }
      ],
      "events": [
        {
          "id": "Sp",
          "modality": "Sp",
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "Si_action",
          "modality": "Si_action",
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action",
          "modality": "So_action",
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "content": {
        "Sp": {
          "actor": "person_A",
          "text": "help",
          "definition": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        "Si_action": {
          "actor": "person_A",
          "action": "thumbs_up",
          "body_side": "right",
          "body_part": "hand",
          "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        "So_action": {
          "actor": "person_A",
          "action": "slapping_the_thigh",
          "acting_body_side": "right",
          "acting_body_part": "hand",
          "target_body_side": "right",
          "target_body_part": "thigh",
          "target_sound": "sharp slap sound",
          "definition": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      },
      "temporal_constraint": {
        "relation_type": "order",
        "timing_type": "absolute",
        "value": {
          "schedule": [
            {
              "time_sec": 1.0,
              "events": [
                "Sp"
              ]
            },
            {
              "time_sec": 2.5,
              "events": [
                "So_action"
              ]
            },
            {
              "time_sec": 4.0,
              "events": [
                "Si_action"
              ]
            }
          ]
        }
      }
    },
    "evaluationItems": {
      "audio_content": [
        {
          "id": "Sp_audio",
          "title": "Speech: \"help\"",
          "description": "The person clearly says the single word \"help\". The Sp is audible and easy to distinguish. No extra words are spoken unless explicitly required."
        },
        {
          "id": "So_action_sound",
          "title": "Sharp slap sound",
          "description": "The required sound is present: sharp slap sound."
        }
      ],
      "visual_content": [
        {
          "id": "Si_action_visual",
          "title": "Right thumbs up",
          "description": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
        },
        {
          "id": "So_action_visual",
          "title": "Right slapping the thigh",
          "description": "The person's right hand strikes the top of the person's right thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
        }
      ],
      "audio_visual_sync": [
        {
          "id": "Sp_mouth_audio_alignment",
          "title": "Speech: \"help\" audio-mouth alignment",
          "description": "The spoken word is audible and aligns with visible mouth movement when mouth movement is visible."
        },
        {
          "id": "So_action_sound_visual_alignment",
          "title": "Sharp slap sound aligned with visible action",
          "description": "The sound occurs at the same time as the corresponding visible action/contact."
        }
      ],
      "temporal_relation": [
        {
          "id": "order_relation",
          "title": "Order",
          "description": "speech at 1.0s; thigh slap at 2.5s; thumbs-up at 4.0s"
        }
      ],
      "temporal_count": [
        {
          "id": "Sp_count",
          "title": "Speech",
          "description": "Enter how many times the speech event occurs in the video."
        },
        {
          "id": "So_action_count",
          "title": "Thigh slap",
          "description": "Enter how many times the thigh slap event occurs in the video."
        },
        {
          "id": "Si_action_count",
          "title": "Thumbs-up",
          "description": "Enter how many times the thumbs-up event occurs in the video."
        }
      ],
      "constraint_following": [
        {
          "id": "overall_constraints",
          "title": "Constraints",
          "description": "Scene: plain indoor room. Camera: static medium shot. After the final event, no new target action occurs."
        }
      ]
    }
  }
];

export default initialVideos;