{
 "S8sh1": {
  "input_fingerprint": "f67d0981cb47dfe1",
  "geometry": {
   "camera": {
    "look_target": {
     "x": 0.35,
     "y": 0.58
    },
    "origin": {
     "x": 0.43,
     "y": 0.58
    }
   },
   "entity_placements": [
    {
     "slot": "E1",
     "subject_en": "young woman riding a bicycle",
     "x": 0.35,
     "y": 0.58
    }
   ],
   "rationale_ko": "자전거를 탄 여성은 네온사인(C2)이 이어지는 항구 인접 상업도로(C1) 위에서 마트 입구 접근부(E3)로 향하는 위치에 배치했다. 카메라는 도로의 마트 쪽 가장자리에서 일정한 측면 거리를 두고 서쪽을 바라보게 하여, 도로 진행축과 직각인 완전한 측면 전신 및 페달링 자세를 담고 뒤쪽으로 네온사인과 항구 방향(C3)이 겹쳐 보이도록 설정했다."
  },
  "leakage": {
   "has_marker_leakage": false,
   "details_ko": "다이어그램 기호나 도면 유출이 없습니다."
  },
  "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached TOP-DOWN SITE PLAN, seen from the camera position\ngiven in the STAGING GEOMETRY data below.\n\nJurisdiction of sources — follow all three, they do not conflict:\n- The attached SITE PLAN is the SOT for what exists on the site and\n  how its zones and landmarks are arranged relative to each other.\n- The STAGING GEOMETRY data below is the SOT for XY POSITIONS and\n  horizontal heading ONLY: where each subject stands on that plan,\n  where the camera stands, and which way it looks. Distances,\n  directions and relative depths between subjects come from these\n  coordinates. Subjects outside the camera's horizontal field of\n  view are out of frame.\n- The CAMERA DIRECTION text below (when present) is the SOT for the\n  VERTICAL angle, elevation, tilt and framing (eye-level, high angle,\n  overhead crane, low angle, ...). If it asks for a high or overhead\n  angle, draw that angle — the site plan being top-down does NOT mean\n  the frame must be eye-level.\n\nSTYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain\npaper. No shading, no hatching, no texture, no facial features beyond\na minimal head shape, no costume detail. Human figures are correctly\nproportioned full-body outlines in their canonical poses. Environment\nis reduced to a few placement lines (ground line, key landmark\nsilhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow are normalized map coordinates on the attached site plan\n(x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to\nplace the camera and subjects. Do NOT draw any of this data in the\nimage — no numbers, no coordinates, no labels, no arrows, no cones,\nno dots, no diagram symbols of any kind.\n- the camera stands at (x=0.43, y=0.58) and looks toward (x=0.35, y=0.58); subjects outside the camera's horizontal field of view are out of frame\n- young woman riding a bicycle stands at (x=0.35, y=0.58)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Track parallel from the street side at the prescribed lateral distance and low-to-mid height, keeping 수리영 and the bicycle in complete profile. Her full pedaling posture occupies the middle third while taxis, neon signs, and street stalls pass in layered background bands without obscuring her path.\n\nTHE LOCATION: 대형 마트 외부와 입구\n\nSHOT TEXT (authoritative, Korean): 네온사인과 포장마차가 늘어선 번화가 거리에서 자전거 안장에 앉아 한쪽 무릎은 내려가고 반대쪽 무릎은 올라온 페달링 중 자세의 수리영 전신.\n\nCRITICAL — THE SITE PLAN IS A STAGING REFERENCE, NOT CONTENT: do NOT\ndraw the plan itself, and do NOT draw any diagram elements in the\nframe — no circles, dots, wedges, cones, arrows, callouts, codes or\nany other overlay symbols. The output is a clean storyboard drawing\nof the scene as seen by the camera only.\n\nNo text, no letters, no numbers, no captions anywhere in the image."
 },
 "S15sh6": {
  "input_fingerprint": "997c082d94a432c6",
  "geometry": {
   "camera": {
    "look_target": {
     "x": 0.5,
     "y": 0.49
    },
    "origin": {
     "x": 0.375,
     "y": 0.65
    }
   },
   "entity_placements": [
    {
     "slot": "E1",
     "subject_en": "standing woman near the bus-stop bench",
     "x": 0.466,
     "y": 0.47
    },
    {
     "slot": "E2",
     "subject_en": "running young woman with one leg lifted",
     "x": 0.531,
     "y": 0.505
    }
   ],
   "rationale_ko": "카메라는 B1 남서쪽 풀숲 안의 낮은 위치에서 버스정류장 쪽을 정적으로 바라보게 했다. 혜수는 정류장 벤치 가까운 왼쪽에 멈춰 세우고, 수리영은 충분히 분리된 오른쪽 도로변에서 한쪽 다리를 든 채 달리는 순간으로 배치해 두 인물이 풀숲 틈 너머의 먼 실루엣으로 보이게 했다."
  },
  "leakage": {
   "has_marker_leakage": false,
   "details_ko": "마커나 다이어그램 기호 없이 지시된 카메라 시점만 묘사되었습니다."
  },
  "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached TOP-DOWN SITE PLAN, seen from the camera position\ngiven in the STAGING GEOMETRY data below.\n\nJurisdiction of sources — follow all three, they do not conflict:\n- The attached SITE PLAN is the SOT for what exists on the site and\n  how its zones and landmarks are arranged relative to each other.\n- The STAGING GEOMETRY data below is the SOT for XY POSITIONS and\n  horizontal heading ONLY: where each subject stands on that plan,\n  where the camera stands, and which way it looks. Distances,\n  directions and relative depths between subjects come from these\n  coordinates. Subjects outside the camera's horizontal field of\n  view are out of frame.\n- The CAMERA DIRECTION text below (when present) is the SOT for the\n  VERTICAL angle, elevation, tilt and framing (eye-level, high angle,\n  overhead crane, low angle, ...). If it asks for a high or overhead\n  angle, draw that angle — the site plan being top-down does NOT mean\n  the frame must be eye-level.\n\nSTYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain\npaper. No shading, no hatching, no texture, no facial features beyond\na minimal head shape, no costume detail. Human figures are correctly\nproportioned full-body outlines in their canonical poses. Environment\nis reduced to a few placement lines (ground line, key landmark\nsilhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow are normalized map coordinates on the attached site plan\n(x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to\nplace the camera and subjects. Do NOT draw any of this data in the\nimage — no numbers, no coordinates, no labels, no arrows, no cones,\nno dots, no diagram symbols of any kind.\n- the camera stands at (x=0.38, y=0.65) and looks toward (x=0.50, y=0.49); subjects outside the camera's horizontal field of view are out of frame\n- standing woman near the bus-stop bench stands at (x=0.47, y=0.47)\n- running young woman with one leg lifted stands at (x=0.53, y=0.51)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): From a low, static position within the grass, the camera watches through a narrow irregular gap, with nearby blades obscuring portions of the lower and side edges without overwhelming the distant figures. 수리영 is caught mid-stride toward the right with one leg lifted, while 혜수 remains clearly separated to the left near the bench, both reduced to distant silhouettes.\n\nTHE LOCATION: 해안가 버스정류장\n\nSHOT TEXT (authoritative, Korean): 풀숲 그림자에 반쯤 가려진 불길한 주관적 시야 틈새로, 멀찍이 서 있는 혜수와 한쪽 다리를 공중에 띄운 채 달려가는 자세인 수리영의 실루엣이 담긴 구도.\n\nCRITICAL — THE SITE PLAN IS A STAGING REFERENCE, NOT CONTENT: do NOT\ndraw the plan itself, and do NOT draw any diagram elements in the\nframe — no circles, dots, wedges, cones, arrows, callouts, codes or\nany other overlay symbols. The output is a clean storyboard drawing\nof the scene as seen by the camera only.\n\nNo text, no letters, no numbers, no captions anywhere in the image."
 }
}