{
  "schema_version": 1,
  "concept_key": "want",
  "video_count": 3,
  "scripts": [
    {
      "video_key": "want_context_01",
      "purpose": "model",
      "duration_seconds": 8,
      "format": "16:9 landscape",
      "frame_rate": "25 or 30 fps constant",
      "resolution": "1920x1080 minimum",
      "reference_setup_image": "want_context_01_setup_01.png",
      "reference_concept_image": "../images/want_isolated_01.png",
      "story_summary": "A 5-8 second close, uncluttered real-world demonstration of want, with a clear start and finish.",
      "setting": "plain warm-white studio table",
      "people": "one AI-generated child",
      "target_depiction": "South Asian child pointing and reaching toward a red ball beside a blue block",
      "timeline": [
        {
          "timecode": "00:00.000-00:01.500",
          "picture": "Establish the everyday situation and communication partner or meaningful cause.",
          "performance": "Settle naturally; no one looks at camera unless the communicative meaning requires partner gaze.",
          "camera": "Locked establishing view; level horizon; no handheld shake.",
          "audio": "Capture clean room tone only.",
          "edit": "Start from a clean stable frame; no title card."
        },
        {
          "timecode": "00:01.500-00:05.500",
          "picture": "Show the target intent or emotion with congruent facial, body and contextual cues: South Asian child pointing and reaching toward a red ball beside a blue block.",
          "performance": "Let the context motivate the response naturally: South Asian child pointing and reaching toward a red ball beside a blue block. Use congruent face, body and partner response without exaggeration.",
          "camera": "Medium-close teaching view; keep the target, relevant hands, reference object and face in focus.",
          "audio": "Natural production sound at low level; no spoken label is required.",
          "edit": "One continuous take preferred; one motivated straight cut permitted."
        },
        {
          "timecode": "00:05.500-00:08.000",
          "picture": "Show an appropriate partner response or stable emotional aftermath; preserve autonomy and natural expression.",
          "performance": "Hold the completed meaning without pointing, celebration or repeated action.",
          "camera": "Locked result frame with at least 5 percent safe margin around the target.",
          "audio": "Continue matching room tone; fade neither picture nor sound before 8 seconds.",
          "edit": "End on a stable frame suitable for pausing."
        }
      ],
      "camera_direction": {
        "lens_equivalent": "35-50 mm natural perspective; 70-85 mm for isolated face detail",
        "height": "target or seated eye level",
        "movement": "locked-off; optional imperceptibly slow push-in",
        "focus": "sufficient depth of field to keep semantic evidence sharp",
        "exposure": "natural skin tones and no clipped highlights",
        "white_balance": "locked throughout",
        "continuity_locks": [
          "participant identity",
          "clothing",
          "target instance",
          "background layout",
          "lighting direction"
        ]
      },
      "performance_direction": {
        "primary": "Let the context motivate the response naturally: South Asian child pointing and reaching toward a red ball beside a blue block. Use congruent face, body and partner response without exaggeration.",
        "pace": "natural and readable, never slow-motion acting",
        "gaze": "natural task or partner gaze; never require eye contact",
        "repetitions": "one complete target event",
        "safeguarding": "stop on discomfort; no forced compliance or distress performance"
      },
      "spoken_script": {
        "required": false,
        "dialogue": [],
        "localized_voiceover_optional": "Use the approved localized semantic label or instruction for want only after SLP and native review.",
        "record_separately": true
      },
      "caption_script": {
        "language": "en",
        "picture_only_policy": "Do not caption visual action as sound. Leave captions off when the final mix contains no speech or meaningful sound.",
        "cues": [
          {
            "start": "00:01.500",
            "end": "00:05.500",
            "text": "[Quiet everyday room ambience]"
          }
        ],
        "localized_caption_requirement": "Create from the locked final audio, not by translating this draft blindly."
      },
      "audio_description": {
        "language": "en",
        "script": "In plain warm-white studio table, South Asian child pointing and reaching toward a red ball beside a blue block.",
        "delivery": "neutral concise present tense; place in a natural pause or provide as separate accessible track",
        "review": "SLP and blind/low-vision accessibility review required"
      },
      "accessibility_notes": [
        "Meaning must be understandable with audio muted.",
        "Do not use speech, music, colour, camera movement or a transient cue as the only signal.",
        "Keep target visible for at least two seconds after the event.",
        "No flash, flicker, rapid cut, whip pan or unexpected loud sound.",
        "Provide player pause, replay, captions toggle and audio-description track where supported.",
        "Check target contrast and visibility at 320-pixel-wide playback."
      ],
      "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'Want' (key want), purpose model. Use the approved reference image want_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: South Asian child pointing and reaching toward a red ball beside a blue block in plain warm-white studio table; participants: one AI-generated child. Begin with a stable establishing view, show one slow natural target action or reveal, then hold the completed meaning for at least two seconds. Keep the target continuously visible, anatomically and physically plausible, safely framed and naturally lit. Use at most one simple camera cut; no fast zoom, montage or dramatic acting. Language-neutral: no necessary speech and no embedded writing. Preserve culturally respectful, disability-inclusive representation.",
      "negative_prompt": "no captions, labels, readable text, letters, numbers, logos, brands or watermark; no jump cuts, time lapse, fast camera movement, flicker, strobe, looping discontinuity or motion smear; no extra fingers, fused limbs, changing identity, changing clothing, morphing objects or disappearing props; no unsafe, frightening, coercive, humiliating or medically distressing behavior; no target hidden by hands, crop, foreground objects or shallow focus at the teaching moment; no music as a meaning cue and no speech required to understand the concept",
      "generation_settings": {
        "aspect_ratio": "16:9",
        "duration_seconds": 8,
        "camera_motion": "locked",
        "seed": "record exact provider seed when available",
        "reference_strength": "preserve semantics and composition; do not clone a real identity",
        "generate_audio": false
      },
      "continuity_review": [
        "same participant identity and anatomy",
        "same clothing and assistive devices",
        "same target object and quantity",
        "hands remain anatomically plausible",
        "background objects do not appear or disappear",
        "action begins and ends logically"
      ],
      "delivery": {
        "video_filename": "want_context_01.mp4",
        "caption_filename": "want_context_01.captions.<language>.vtt",
        "audio_description_filename": "want_context_01.audio_description.<language>.wav",
        "poster_filename": "want_context_01.poster.png"
      },
      "status": "script_ready_review_required"
    },
    {
      "video_key": "want_context_02",
      "purpose": "functional_context",
      "duration_seconds": 8,
      "format": "16:9 landscape",
      "frame_rate": "25 or 30 fps constant",
      "resolution": "1920x1080 minimum",
      "reference_setup_image": "want_context_02_setup_01.png",
      "reference_concept_image": "../images/want_natural_context_01.png",
      "story_summary": "A 6-10 second natural interaction showing want with a different person and setting; no acting exaggeration.",
      "setting": "home snack table",
      "people": "one AI-generated child and one AI-generated adult",
      "target_depiction": "East Asian child selecting a banana instead of water from a Black adult",
      "timeline": [
        {
          "timecode": "00:00.000-00:01.500",
          "picture": "Establish the everyday situation and communication partner or meaningful cause.",
          "performance": "Settle naturally; no one looks at camera unless the communicative meaning requires partner gaze.",
          "camera": "Locked establishing view; level horizon; no handheld shake.",
          "audio": "Capture clean room tone only.",
          "edit": "Start from a clean stable frame; no title card."
        },
        {
          "timecode": "00:01.500-00:05.500",
          "picture": "Show the target intent or emotion with congruent facial, body and contextual cues: East Asian child selecting a banana instead of water from a Black adult.",
          "performance": "Let the context motivate the response naturally: East Asian child selecting a banana instead of water from a Black adult. Use congruent face, body and partner response without exaggeration.",
          "camera": "Medium-close teaching view; keep the target, relevant hands, reference object and face in focus.",
          "audio": "Natural production sound at low level; no spoken label is required.",
          "edit": "One continuous take preferred; one motivated straight cut permitted."
        },
        {
          "timecode": "00:05.500-00:08.000",
          "picture": "Show an appropriate partner response or stable emotional aftermath; preserve autonomy and natural expression.",
          "performance": "Hold the completed meaning without pointing, celebration or repeated action.",
          "camera": "Locked result frame with at least 5 percent safe margin around the target.",
          "audio": "Continue matching room tone; fade neither picture nor sound before 8 seconds.",
          "edit": "End on a stable frame suitable for pausing."
        }
      ],
      "camera_direction": {
        "lens_equivalent": "35-50 mm natural perspective; 70-85 mm for isolated face detail",
        "height": "target or seated eye level",
        "movement": "locked-off; optional imperceptibly slow push-in",
        "focus": "sufficient depth of field to keep semantic evidence sharp",
        "exposure": "natural skin tones and no clipped highlights",
        "white_balance": "locked throughout",
        "continuity_locks": [
          "participant identity",
          "clothing",
          "target instance",
          "background layout",
          "lighting direction"
        ]
      },
      "performance_direction": {
        "primary": "Let the context motivate the response naturally: East Asian child selecting a banana instead of water from a Black adult. Use congruent face, body and partner response without exaggeration.",
        "pace": "natural and readable, never slow-motion acting",
        "gaze": "natural task or partner gaze; never require eye contact",
        "repetitions": "one complete target event",
        "safeguarding": "stop on discomfort; no forced compliance or distress performance"
      },
      "spoken_script": {
        "required": false,
        "dialogue": [],
        "localized_voiceover_optional": "Use the approved localized semantic label or instruction for want only after SLP and native review.",
        "record_separately": true
      },
      "caption_script": {
        "language": "en",
        "picture_only_policy": "Do not caption visual action as sound. Leave captions off when the final mix contains no speech or meaningful sound.",
        "cues": [
          {
            "start": "00:01.500",
            "end": "00:05.500",
            "text": "[Quiet everyday room ambience]"
          }
        ],
        "localized_caption_requirement": "Create from the locked final audio, not by translating this draft blindly."
      },
      "audio_description": {
        "language": "en",
        "script": "In home snack table, East Asian child selecting a banana instead of water from a Black adult.",
        "delivery": "neutral concise present tense; place in a natural pause or provide as separate accessible track",
        "review": "SLP and blind/low-vision accessibility review required"
      },
      "accessibility_notes": [
        "Meaning must be understandable with audio muted.",
        "Do not use speech, music, colour, camera movement or a transient cue as the only signal.",
        "Keep target visible for at least two seconds after the event.",
        "No flash, flicker, rapid cut, whip pan or unexpected loud sound.",
        "Provide player pause, replay, captions toggle and audio-description track where supported.",
        "Check target contrast and visibility at 320-pixel-wide playback."
      ],
      "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'Want' (key want), purpose functional_context. Use the approved reference image want_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: East Asian child selecting a banana instead of water from a Black adult in home snack table; participants: one AI-generated child and one AI-generated adult. Begin with a stable establishing view, show one slow natural target action or reveal, then hold the completed meaning for at least two seconds. Keep the target continuously visible, anatomically and physically plausible, safely framed and naturally lit. Use at most one simple camera cut; no fast zoom, montage or dramatic acting. Language-neutral: no necessary speech and no embedded writing. Preserve culturally respectful, disability-inclusive representation.",
      "negative_prompt": "no captions, labels, readable text, letters, numbers, logos, brands or watermark; no jump cuts, time lapse, fast camera movement, flicker, strobe, looping discontinuity or motion smear; no extra fingers, fused limbs, changing identity, changing clothing, morphing objects or disappearing props; no unsafe, frightening, coercive, humiliating or medically distressing behavior; no target hidden by hands, crop, foreground objects or shallow focus at the teaching moment; no music as a meaning cue and no speech required to understand the concept",
      "generation_settings": {
        "aspect_ratio": "16:9",
        "duration_seconds": 8,
        "camera_motion": "locked",
        "seed": "record exact provider seed when available",
        "reference_strength": "preserve semantics and composition; do not clone a real identity",
        "generate_audio": false
      },
      "continuity_review": [
        "same participant identity and anatomy",
        "same clothing and assistive devices",
        "same target object and quantity",
        "hands remain anatomically plausible",
        "background objects do not appear or disappear",
        "action begins and ends logically"
      ],
      "delivery": {
        "video_filename": "want_context_02.mp4",
        "caption_filename": "want_context_02.captions.<language>.vtt",
        "audio_description_filename": "want_context_02.audio_description.<language>.wav",
        "poster_filename": "want_context_02.poster.png"
      },
      "status": "script_ready_review_required"
    },
    {
      "video_key": "want_context_03",
      "purpose": "generalisation",
      "duration_seconds": 8,
      "format": "16:9 landscape",
      "frame_rate": "25 or 30 fps constant",
      "resolution": "1920x1080 minimum",
      "reference_setup_image": "want_context_03_setup_01.png",
      "reference_concept_image": "../images/want_unfamiliar_01.png",
      "story_summary": "A novel 6-10 second example of want for generalisation, with the target moment visible without narration.",
      "setting": "calm home living room",
      "people": "two AI-generated adults",
      "target_depiction": "Older East Asian woman selecting a lavender blanket instead of water from a Black adult",
      "timeline": [
        {
          "timecode": "00:00.000-00:01.500",
          "picture": "Establish the everyday situation and communication partner or meaningful cause.",
          "performance": "Settle naturally; no one looks at camera unless the communicative meaning requires partner gaze.",
          "camera": "Locked establishing view; level horizon; no handheld shake.",
          "audio": "Capture clean room tone only.",
          "edit": "Start from a clean stable frame; no title card."
        },
        {
          "timecode": "00:01.500-00:05.500",
          "picture": "Show the target intent or emotion with congruent facial, body and contextual cues: Older East Asian woman selecting a lavender blanket instead of water from a Black adult.",
          "performance": "Let the context motivate the response naturally: Older East Asian woman selecting a lavender blanket instead of water from a Black adult. Use congruent face, body and partner response without exaggeration.",
          "camera": "Medium-close teaching view; keep the target, relevant hands, reference object and face in focus.",
          "audio": "Natural production sound at low level; no spoken label is required.",
          "edit": "One continuous take preferred; one motivated straight cut permitted."
        },
        {
          "timecode": "00:05.500-00:08.000",
          "picture": "Show an appropriate partner response or stable emotional aftermath; preserve autonomy and natural expression.",
          "performance": "Hold the completed meaning without pointing, celebration or repeated action.",
          "camera": "Locked result frame with at least 5 percent safe margin around the target.",
          "audio": "Continue matching room tone; fade neither picture nor sound before 8 seconds.",
          "edit": "End on a stable frame suitable for pausing."
        }
      ],
      "camera_direction": {
        "lens_equivalent": "35-50 mm natural perspective; 70-85 mm for isolated face detail",
        "height": "target or seated eye level",
        "movement": "locked-off; optional imperceptibly slow push-in",
        "focus": "sufficient depth of field to keep semantic evidence sharp",
        "exposure": "natural skin tones and no clipped highlights",
        "white_balance": "locked throughout",
        "continuity_locks": [
          "participant identity",
          "clothing",
          "target instance",
          "background layout",
          "lighting direction"
        ]
      },
      "performance_direction": {
        "primary": "Let the context motivate the response naturally: Older East Asian woman selecting a lavender blanket instead of water from a Black adult. Use congruent face, body and partner response without exaggeration.",
        "pace": "natural and readable, never slow-motion acting",
        "gaze": "natural task or partner gaze; never require eye contact",
        "repetitions": "one complete target event",
        "safeguarding": "stop on discomfort; no forced compliance or distress performance"
      },
      "spoken_script": {
        "required": false,
        "dialogue": [],
        "localized_voiceover_optional": "Use the approved localized semantic label or instruction for want only after SLP and native review.",
        "record_separately": true
      },
      "caption_script": {
        "language": "en",
        "picture_only_policy": "Do not caption visual action as sound. Leave captions off when the final mix contains no speech or meaningful sound.",
        "cues": [
          {
            "start": "00:01.500",
            "end": "00:05.500",
            "text": "[Quiet everyday room ambience]"
          }
        ],
        "localized_caption_requirement": "Create from the locked final audio, not by translating this draft blindly."
      },
      "audio_description": {
        "language": "en",
        "script": "In calm home living room, Older East Asian woman selecting a lavender blanket instead of water from a Black adult.",
        "delivery": "neutral concise present tense; place in a natural pause or provide as separate accessible track",
        "review": "SLP and blind/low-vision accessibility review required"
      },
      "accessibility_notes": [
        "Meaning must be understandable with audio muted.",
        "Do not use speech, music, colour, camera movement or a transient cue as the only signal.",
        "Keep target visible for at least two seconds after the event.",
        "No flash, flicker, rapid cut, whip pan or unexpected loud sound.",
        "Provide player pause, replay, captions toggle and audio-description track where supported.",
        "Check target contrast and visibility at 320-pixel-wide playback."
      ],
      "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'Want' (key want), purpose generalisation. Use the approved reference image want_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: Older East Asian woman selecting a lavender blanket instead of water from a Black adult in calm home living room; participants: two AI-generated adults. Begin with a stable establishing view, show one slow natural target action or reveal, then hold the completed meaning for at least two seconds. Keep the target continuously visible, anatomically and physically plausible, safely framed and naturally lit. Use at most one simple camera cut; no fast zoom, montage or dramatic acting. Language-neutral: no necessary speech and no embedded writing. Preserve culturally respectful, disability-inclusive representation.",
      "negative_prompt": "no captions, labels, readable text, letters, numbers, logos, brands or watermark; no jump cuts, time lapse, fast camera movement, flicker, strobe, looping discontinuity or motion smear; no extra fingers, fused limbs, changing identity, changing clothing, morphing objects or disappearing props; no unsafe, frightening, coercive, humiliating or medically distressing behavior; no target hidden by hands, crop, foreground objects or shallow focus at the teaching moment; no music as a meaning cue and no speech required to understand the concept",
      "generation_settings": {
        "aspect_ratio": "16:9",
        "duration_seconds": 8,
        "camera_motion": "locked",
        "seed": "record exact provider seed when available",
        "reference_strength": "preserve semantics and composition; do not clone a real identity",
        "generate_audio": false
      },
      "continuity_review": [
        "same participant identity and anatomy",
        "same clothing and assistive devices",
        "same target object and quantity",
        "hands remain anatomically plausible",
        "background objects do not appear or disappear",
        "action begins and ends logically"
      ],
      "delivery": {
        "video_filename": "want_context_03.mp4",
        "caption_filename": "want_context_03.captions.<language>.vtt",
        "audio_description_filename": "want_context_03.audio_description.<language>.wav",
        "poster_filename": "want_context_03.poster.png"
      },
      "status": "script_ready_review_required"
    }
  ],
  "approval": {
    "clinical": false,
    "cultural": false,
    "accessibility": false,
    "rights": false,
    "technical": false
  }
}