{
  "schema_version": 1,
  "concept_key": "school",
  "format": "landscape_16_9",
  "default_duration_seconds": 8,
  "videos": [
    {
      "video_key": "school_context_01",
      "purpose": "model",
      "duration_seconds": 8,
      "reference_image": {
        "asset_key": "school_isolated_01",
        "filename": "../images/school_isolated_01.png",
        "usage": "semantic_and_composition_reference"
      },
      "narrative_intent": "A 5-8 second slow reveal and natural interaction with school, keeping the target in frame.",
      "setup": {
        "setting": "tidy school exterior",
        "depiction": "welcoming elementary school building viewed from front",
        "people": "no people",
        "continuity_lock": [
          "participant identity",
          "clothing",
          "target instance",
          "background layout",
          "lighting direction"
        ]
      },
      "story_beats": [
        {
          "timecode": "0.0-2.0",
          "story_beat": "Begin with a wider contextual view that establishes role or place through ordinary activity."
        },
        {
          "timecode": "2.0-5.5",
          "story_beat": "Move or cut once to the key identifying evidence: welcoming elementary school building viewed from front."
        },
        {
          "timecode": "5.5-8.0",
          "story_beat": "Hold a natural stable view; avoid posed gestures, uniforms or symbols as the sole cue."
        }
      ],
      "shot_list": [
        {
          "shot": 1,
          "framing": "wide or medium establishing shot",
          "movement": "locked-off or very slow push-in",
          "focus": "context plus target",
          "duration_seconds": 2
        },
        {
          "shot": 2,
          "framing": "medium close shot",
          "movement": "locked-off",
          "focus": "target, actor hands and relevant reference object",
          "duration_seconds": 4
        },
        {
          "shot": 3,
          "framing": "close result or response shot",
          "movement": "locked-off",
          "focus": "unambiguous completed meaning",
          "duration_seconds": 2
        }
      ],
      "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'School' (key school), purpose model. Use the approved reference image school_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: welcoming elementary school building viewed from front in tidy school exterior; participants: no people. 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_constraints": [
        "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"
      ],
      "audio_plan": {
        "production_audio": "quiet natural room tone only",
        "speech": "none required",
        "music": "none",
        "localized_voiceover": "optional separate approved track"
      },
      "accessibility": {
        "captions": "required if any speech is added",
        "audio_description": "author from narrative_intent after picture lock",
        "photosensitivity": "no flashes or rapid cuts",
        "silent_comprehension": "required"
      },
      "safety_and_semantics": [
        "Use safe everyday contexts, respectful representation and culturally familiar alternatives; avoid stereotypes and coercion.",
        "Localize from semantic intent rather than translating the English label literally.",
        "Clinical and native-language/cultural review are required before approval."
      ],
      "review_gates": [
        "technical continuity",
        "target clarity",
        "SLP review",
        "accessibility review",
        "cultural review",
        "rights and releases"
      ],
      "status": "prompt_ready_review_required"
    },
    {
      "video_key": "school_context_02",
      "purpose": "functional_context",
      "duration_seconds": 8,
      "reference_image": {
        "asset_key": "school_natural_context_01",
        "filename": "../images/school_natural_context_01.png",
        "usage": "semantic_and_composition_reference"
      },
      "narrative_intent": "A 6-10 second functional everyday use of school by a person, without unnecessary spoken language.",
      "setup": {
        "setting": "bright organized classroom",
        "depiction": "teacher instructing four children at classroom desks",
        "people": "five AI-generated people",
        "continuity_lock": [
          "participant identity",
          "clothing",
          "target instance",
          "background layout",
          "lighting direction"
        ]
      },
      "story_beats": [
        {
          "timecode": "0.0-2.0",
          "story_beat": "Begin with a wider contextual view that establishes role or place through ordinary activity."
        },
        {
          "timecode": "2.0-5.5",
          "story_beat": "Move or cut once to the key identifying evidence: teacher instructing four children at classroom desks."
        },
        {
          "timecode": "5.5-8.0",
          "story_beat": "Hold a natural stable view; avoid posed gestures, uniforms or symbols as the sole cue."
        }
      ],
      "shot_list": [
        {
          "shot": 1,
          "framing": "wide or medium establishing shot",
          "movement": "locked-off or very slow push-in",
          "focus": "context plus target",
          "duration_seconds": 2
        },
        {
          "shot": 2,
          "framing": "medium close shot",
          "movement": "locked-off",
          "focus": "target, actor hands and relevant reference object",
          "duration_seconds": 4
        },
        {
          "shot": 3,
          "framing": "close result or response shot",
          "movement": "locked-off",
          "focus": "unambiguous completed meaning",
          "duration_seconds": 2
        }
      ],
      "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'School' (key school), purpose functional_context. Use the approved reference image school_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: teacher instructing four children at classroom desks in bright organized classroom; participants: five AI-generated people. 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_constraints": [
        "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"
      ],
      "audio_plan": {
        "production_audio": "quiet natural room tone only",
        "speech": "none required",
        "music": "none",
        "localized_voiceover": "optional separate approved track"
      },
      "accessibility": {
        "captions": "required if any speech is added",
        "audio_description": "author from narrative_intent after picture lock",
        "photosensitivity": "no flashes or rapid cuts",
        "silent_comprehension": "required"
      },
      "safety_and_semantics": [
        "Use safe everyday contexts, respectful representation and culturally familiar alternatives; avoid stereotypes and coercion.",
        "Localize from semantic intent rather than translating the English label literally.",
        "Clinical and native-language/cultural review are required before approval."
      ],
      "review_gates": [
        "technical continuity",
        "target clarity",
        "SLP review",
        "accessibility review",
        "cultural review",
        "rights and releases"
      ],
      "status": "prompt_ready_review_required"
    },
    {
      "video_key": "school_context_03",
      "purpose": "generalisation",
      "duration_seconds": 8,
      "reference_image": {
        "asset_key": "school_unfamiliar_01",
        "filename": "../images/school_unfamiliar_01.png",
        "usage": "semantic_and_composition_reference"
      },
      "narrative_intent": "A 6-10 second novel setting or instance of school for generalisation.",
      "setup": {
        "setting": "rural roofed school pavilion",
        "depiction": "teacher and six children learning in an open-air classroom",
        "people": "seven AI-generated people",
        "continuity_lock": [
          "participant identity",
          "clothing",
          "target instance",
          "background layout",
          "lighting direction"
        ]
      },
      "story_beats": [
        {
          "timecode": "0.0-2.0",
          "story_beat": "Begin with a wider contextual view that establishes role or place through ordinary activity."
        },
        {
          "timecode": "2.0-5.5",
          "story_beat": "Move or cut once to the key identifying evidence: teacher and six children learning in an open-air classroom."
        },
        {
          "timecode": "5.5-8.0",
          "story_beat": "Hold a natural stable view; avoid posed gestures, uniforms or symbols as the sole cue."
        }
      ],
      "shot_list": [
        {
          "shot": 1,
          "framing": "wide or medium establishing shot",
          "movement": "locked-off or very slow push-in",
          "focus": "context plus target",
          "duration_seconds": 2
        },
        {
          "shot": 2,
          "framing": "medium close shot",
          "movement": "locked-off",
          "focus": "target, actor hands and relevant reference object",
          "duration_seconds": 4
        },
        {
          "shot": 3,
          "framing": "close result or response shot",
          "movement": "locked-off",
          "focus": "unambiguous completed meaning",
          "duration_seconds": 2
        }
      ],
      "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'School' (key school), purpose generalisation. Use the approved reference image school_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: teacher and six children learning in an open-air classroom in rural roofed school pavilion; participants: seven AI-generated people. 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_constraints": [
        "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"
      ],
      "audio_plan": {
        "production_audio": "quiet natural room tone only",
        "speech": "none required",
        "music": "none",
        "localized_voiceover": "optional separate approved track"
      },
      "accessibility": {
        "captions": "required if any speech is added",
        "audio_description": "author from narrative_intent after picture lock",
        "photosensitivity": "no flashes or rapid cuts",
        "silent_comprehension": "required"
      },
      "safety_and_semantics": [
        "Use safe everyday contexts, respectful representation and culturally familiar alternatives; avoid stereotypes and coercion.",
        "Localize from semantic intent rather than translating the English label literally.",
        "Clinical and native-language/cultural review are required before approval."
      ],
      "review_gates": [
        "technical continuity",
        "target clarity",
        "SLP review",
        "accessibility review",
        "cultural review",
        "rights and releases"
      ],
      "status": "prompt_ready_review_required"
    }
  ]
}
