{
 "S13sh2": {
  "input_fingerprint": "bdf9ce55539a32f6",
  "geometry": {
   "camera": {
    "look_target": {
     "x": 0.53,
     "y": 0.72
    },
    "origin": {
     "x": 0.73,
     "y": 0.86
    }
   },
   "entity_placements": [
    {
     "slot": "E1",
     "subject_en": "dazed standing person",
     "x": 0.5,
     "y": 0.68
    },
    {
     "slot": "E2",
     "subject_en": "running middle-aged policewoman",
     "x": 0.59,
     "y": 0.76
    },
    {
     "slot": "E3",
     "subject_en": "parked police car with flashing lights",
     "x": 0.64,
     "y": 0.71
    }
   ],
   "rationale_ko": "C2 후면 지상 안뜰의 S1 계단 하단 가까이에 멍하니 선 인물을 두고, 경찰차는 그 뒤쪽에 배치했다. 여경은 경찰차에서 계단 방향으로 달려가는 접근선상 중경에 놓아 한 발이 들린 전신 동작을 담는다. 카메라는 같은 접근선 뒤쪽에서 후진 추적하며 여경을 중경, 멈춰 선 인물과 경찰차를 배경에 함께 유지한다."
  },
  "leakage": {
   "has_marker_leakage": false,
   "details_ko": "도면 기호나 텍스트 누출이 발견되지 않았습니다. 지시된 카메라 뷰를 따른 스케치입니다."
  },
  "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=0.73, y=0.86) and looks toward (x=0.53, y=0.72); subjects outside the camera's horizontal field of view are out of frame\n- dazed standing person stands at (x=0.50, y=0.68)\n- running middle-aged policewoman stands at (x=0.59, y=0.76)\n- parked police car with flashing lights stands at (x=0.64, y=0.71)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): At eye height below the stairs, the camera tracks backward along 혜수’s approach line in a wide full-body composition, holding 수리영 near the police car in the background and 혜수 in the advancing midground. The frame is timed to 혜수’s lifted foot, while 수리영 remains fixed and unfocused so only their relative positions change.\n\nTHE LOCATION: 다세대 빌라 마당 및 옥탑방 외부 계단\n\nSHOT TEXT (authoritative, Korean): 경광등이 번쩍이는 경찰차 앞 초점을 잃고 멍하니 선 수리영과, 그를 향해 달려오다 한 발이 땅에서 떨어진 mid-action 순간의 혜수의 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."
 },
 "S15sh5": {
  "input_fingerprint": "cfdd02dcf04659a2",
  "geometry": {
   "camera": {
    "look_target": {
     "x": 0.46,
     "y": 0.71
    },
    "origin": {
     "x": 0.57,
     "y": 0.58
    }
   },
   "entity_placements": [
    {
     "slot": "E1",
     "subject_en": "receding young woman",
     "x": 0.45,
     "y": 0.73
    },
    {
     "slot": "E2",
     "subject_en": "calling woman with cupped hands",
     "x": 0.52,
     "y": 0.62
    }
   ],
   "rationale_ko": "혜수는 B1 해안 버스정류장 남서쪽에 두고, 수리영은 A1 해안 접근 구역의 열린 출발 경로를 따라 더 남서쪽으로 멀어지게 배치했다. 카메라는 혜수 옆의 가까운 위치에서 같은 대각선 방향을 바라보아 혜수를 좌측 전경의 상체 중심으로 잡으면서, 어깨 너머로 작아지는 수리영의 퇴장 방향이 이어지도록 했다."
  },
  "leakage": {
   "has_marker_leakage": false,
   "details_ko": "다이어그램 기호나 텍스트가 노출되지 않은 자연스러운 스케치입니다."
  },
  "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=0.57, y=0.58) and looks toward (x=0.46, y=0.71); subjects outside the camera's horizontal field of view are out of frame\n- receding young woman stands at (x=0.45, y=0.73)\n- calling woman with cupped hands stands at (x=0.52, y=0.62)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Track beside 혜수 at chest height and tighten to her upper body, holding her in the left foreground as her cupped hands reach her mouth. Keep 수리영 small and receding along the same diagonal beyond 혜수's shoulder, so the departing direction remains unmistakable without widening away from 혜수's call.\n\nTHE LOCATION: 해안가 버스정류장 일대\n\nSHOT TEXT (authoritative, Korean): 멀어지는 수리영의 등을 향해 양손을 입가에 모으고 소리치는 혜수의 상체\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."
 }
}