{
 "S1sh7::confined_fp_apt": {
  "applies": false,
  "reason_ko": "이 숏은 요금통 바닥의 동전과 지폐를 바라보는 1인칭 시점의 인서트/클로즈업 숏으로, 버스 내부의 전체적인 좌석 배치나 운전석 조종 장치와의 공간적 위치 관계가 화면에 드러나지 않으므로 평면도 형태의 레이아웃 보조가 필요하지 않습니다.",
  "input_fingerprint": "b27a0e80a0b7e953"
 },
 "S1sh7::signage": {
  "fp": "d3a4b2aa13e56dcf",
  "inscriptions": [],
  "cues": [],
  "dropped": []
 },
 "S1sh7": {
  "input_fingerprint": "3fa5bbb241201984",
  "prompt": "Create ONE FINAL photorealistic live-action film still of the moment below — late 1970s–1980s South Korea; all people are Korean unless stated. TIME OF DAY (lock): evening.\n\nSHOT TEXT (authoritative, Korean): 투명한 요금통 바닥에 깔린 백원짜리 동전들과 접힌 천원권 지폐 두 장을 향한 정임 시점의 1인칭 앵글.\n\nLOCATION (lock): Inside the cramped front fare-collection area of an aging intercity bus, directly beside the driver’s instrument panel and the chained farebox. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: fare box contents in the lower-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: transparent fare box (secured to the column by a chain) — The camera looks steeply through its transparent upper surface toward the contents resting at the bottom; used as Its near rim frames the lower edge of 정임's downward viewpoint without obscuring the money; hundred-won coins (several coins lying at the bottom of the fare box); used as Primary visual evidence scattered around the folded bills in the lower-center frame; two thousand-won bills (both bills folded and lying at the bottom of the fare box) — Their folded outer faces are visible from above, identifying them as the two bills described in the scene; used as Primary focal objects grouped among the coins; fare-box chain (binding the fare box to the adjacent column) — A short linked section enters along the frame edge and leads toward the column; used as Provides peripheral evidence that the box remains fixed in place.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient light appropriate to the evening bus interior, rendered in restrained aged neutrals with low-key contrast and tactile analog texture.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nREALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot\ntext may describe characters metaphorically, figuratively or with\nexaggeration. Photograph what a real movie camera would actually\nrecord on a physical set — exaggerated or figurative impressions\nbecome realistic staging within whatever this brief already fixes,\nnot literal fantasy imagery.\n\nPROPS FACE THE RIGHT WAY: every handheld or used object must be\noriented exactly as its real-world use requires. A person reading,\nwatching or operating something (a phone, a photograph, a paper,\nany device) has its functional side — screen, front, page — facing\nTHEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nDRAWN MARKS KEEP THEIR SHAPE: any mark the text describes as drawn,\npainted or traced (a circle, a line, a symbol) is a STROKE sitting on\nthe surface — an outline whose interior still shows the underlying\nsurface (wall, skin, paper). Render its stated shape faithfully: a\ndrawn circle stays an open ring of brush-width, never filled into a\nsolid disc, unless the text explicitly says it is filled.\n\nCARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The bus retains old vinyl seatback covers, a rubber aisle mat, three round analog gauges, and a fare box chained to the pillar. Several 100-won coins and two folded 1,000-won bills lie on the bottom of the fare box.\n\nNO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person appears in frame, and no face, and no figure standing, sitting or passing through. Do not invent someone to occupy the space.\n\nOne thing this rule does NOT forbid: the hand or arm of whoever is doing what the shot text describes. If the moment is an object being held, carried, operated, read, aimed, worn or handed over, the hand doing it belongs in frame, resting on or gripping that object exactly as its real use requires. An object photographed floating unsupported, with the hand that must be holding it erased, is a worse failure than the person you were avoiding — render the hand.\n\nNo readable writing anywhere in this image. Surfaces that would carry writing may be present, but nothing a viewer could read: stage every one of them out of legibility — a hand across, an oblique angle, shallow focus, or simply turned away. No caption, subtitle, watermark, logo or overlay.",
  "roll_prompts": {
   "A": "Create ONE FINAL photorealistic live-action film still of the moment below — late 1970s–1980s South Korea; all people are Korean unless stated. TIME OF DAY (lock): evening.\n\nSHOT TEXT (authoritative, Korean): 투명한 요금통 바닥에 깔린 백원짜리 동전들과 접힌 천원권 지폐 두 장을 향한 정임 시점의 1인칭 앵글.\n\nLOCATION (lock): Inside the cramped front fare-collection area of an aging intercity bus, directly beside the driver’s instrument panel and the chained farebox. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: fare box contents in the lower-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: transparent fare box (secured to the column by a chain) — The camera looks steeply through its transparent upper surface toward the contents resting at the bottom; used as Its near rim frames the lower edge of 정임's downward viewpoint without obscuring the money; hundred-won coins (several coins lying at the bottom of the fare box); used as Primary visual evidence scattered around the folded bills in the lower-center frame; two thousand-won bills (both bills folded and lying at the bottom of the fare box) — Their folded outer faces are visible from above, identifying them as the two bills described in the scene; used as Primary focal objects grouped among the coins; fare-box chain (binding the fare box to the adjacent column) — A short linked section enters along the frame edge and leads toward the column; used as Provides peripheral evidence that the box remains fixed in place.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient light appropriate to the evening bus interior, rendered in restrained aged neutrals with low-key contrast and tactile analog texture.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nREALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot\ntext may describe characters metaphorically, figuratively or with\nexaggeration. Photograph what a real movie camera would actually\nrecord on a physical set — exaggerated or figurative impressions\nbecome realistic staging within whatever this brief already fixes,\nnot literal fantasy imagery.\n\nPROPS FACE THE RIGHT WAY: every handheld or used object must be\noriented exactly as its real-world use requires. A person reading,\nwatching or operating something (a phone, a photograph, a paper,\nany device) has its functional side — screen, front, page — facing\nTHEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nDRAWN MARKS KEEP THEIR SHAPE: any mark the text describes as drawn,\npainted or traced (a circle, a line, a symbol) is a STROKE sitting on\nthe surface — an outline whose interior still shows the underlying\nsurface (wall, skin, paper). Render its stated shape faithfully: a\ndrawn circle stays an open ring of brush-width, never filled into a\nsolid disc, unless the text explicitly says it is filled.\n\nCARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The bus retains old vinyl seatback covers, a rubber aisle mat, three round analog gauges, and a fare box chained to the pillar. Several 100-won coins and two folded 1,000-won bills lie on the bottom of the fare box.\n\nNO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person appears in frame, and no face, and no figure standing, sitting or passing through. Do not invent someone to occupy the space.\n\nOne thing this rule does NOT forbid: the hand or arm of whoever is doing what the shot text describes. If the moment is an object being held, carried, operated, read, aimed, worn or handed over, the hand doing it belongs in frame, resting on or gripping that object exactly as its real use requires. An object photographed floating unsupported, with the hand that must be holding it erased, is a worse failure than the person you were avoiding — render the hand.\n\nNo readable writing anywhere in this image. Surfaces that would carry writing may be present, but nothing a viewer could read: stage every one of them out of legibility — a hand across, an oblique angle, shallow focus, or simply turned away. No caption, subtitle, watermark, logo or overlay.",
   "B": "Create ONE FINAL photorealistic live-action film still of the moment below — late 1970s–1980s South Korea; all people are Korean unless stated. TIME OF DAY (lock): evening.\n\nSHOT TEXT (authoritative, Korean): 투명한 요금통 바닥에 깔린 백원짜리 동전들과 접힌 천원권 지폐 두 장을 향한 정임 시점의 1인칭 앵글.\n\nLOCATION (lock): Inside the cramped front fare-collection area of an aging intercity bus, directly beside the driver’s instrument panel and the chained farebox. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: fare box contents in the lower-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: transparent fare box (secured to the column by a chain) — The camera looks steeply through its transparent upper surface toward the contents resting at the bottom; used as Its near rim frames the lower edge of 정임's downward viewpoint without obscuring the money; hundred-won coins (several coins lying at the bottom of the fare box); used as Primary visual evidence scattered around the folded bills in the lower-center frame; two thousand-won bills (both bills folded and lying at the bottom of the fare box) — Their folded outer faces are visible from above, identifying them as the two bills described in the scene; used as Primary focal objects grouped among the coins; fare-box chain (binding the fare box to the adjacent column) — A short linked section enters along the frame edge and leads toward the column; used as Provides peripheral evidence that the box remains fixed in place.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient light appropriate to the evening bus interior, rendered in restrained aged neutrals with low-key contrast and tactile analog texture.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nREALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot\ntext may describe characters metaphorically, figuratively or with\nexaggeration. Photograph what a real movie camera would actually\nrecord on a physical set — exaggerated or figurative impressions\nbecome realistic staging within whatever this brief already fixes,\nnot literal fantasy imagery.\n\nPROPS FACE THE RIGHT WAY: every handheld or used object must be\noriented exactly as its real-world use requires. A person reading,\nwatching or operating something (a phone, a photograph, a paper,\nany device) has its functional side — screen, front, page — facing\nTHEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nDRAWN MARKS KEEP THEIR SHAPE: any mark the text describes as drawn,\npainted or traced (a circle, a line, a symbol) is a STROKE sitting on\nthe surface — an outline whose interior still shows the underlying\nsurface (wall, skin, paper). Render its stated shape faithfully: a\ndrawn circle stays an open ring of brush-width, never filled into a\nsolid disc, unless the text explicitly says it is filled.\n\nCARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The bus retains old vinyl seatback covers, a rubber aisle mat, three round analog gauges, and a fare box chained to the pillar. Several 100-won coins and two folded 1,000-won bills lie on the bottom of the fare box.\n\nNO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person appears in frame, and no face, and no figure standing, sitting or passing through. Do not invent someone to occupy the space.\n\nOne thing this rule does NOT forbid: the hand or arm of whoever is doing what the shot text describes. If the moment is an object being held, carried, operated, read, aimed, worn or handed over, the hand doing it belongs in frame, resting on or gripping that object exactly as its real use requires. An object photographed floating unsupported, with the hand that must be holding it erased, is a worse failure than the person you were avoiding — render the hand.\n\nNo readable writing anywhere in this image. Surfaces that would carry writing may be present, but nothing a viewer could read: stage every one of them out of legibility — a hand across, an oblique angle, shallow focus, or simply turned away. No caption, subtitle, watermark, logo or overlay.\n\nCOMPOSITION VARIATION (this candidate only): keep the place, the people and the moment exactly as specified, and keep from the CAMERA & FRAME contract its subject scale, screen placement and key background elements exactly. For this candidate only, its camera angle and height are deliberately left open: choose a camera position distinctly different from the obvious one, as a film director picking a second setup on the same blocking. Stay true to any explicit framing the SHOT TEXT itself dictates."
  },
  "shot_run_spend_attempt_count": 1,
  "readings": [
   {
    "label": "A",
    "direction": "카메라는 요금통의 투명한 윗면을 통해 얕은 하향 각도로 바닥에 놓인 동전과 지폐들을 향하고 있습니다.",
    "built_space": "버스 내부로 배경에 운전석의 스티어링 휠과 계기판이 보입니다. 요금통은 레퍼런스와 일치하는 금속 본체와 투명한 윗면을 가지고 있으며 기둥에 묶여 있습니다.",
    "entities": "투명한 윗면을 가진 요금통, 쇠사슬, 100원짜리 동전들이 보입니다. 그러나 접힌 두 장의 1,000원권 대신, 펴져 있는 1,000원권 한 장과 10,000원권 한 장이 있으며 표면의 한글과 숫자가 매우 선명하게 읽힙니다.",
    "hard_violations": [
     "[gemini-pro] 프롬프트에서 요구하지 않은 발명된 사물(10,000원권 지폐)이 프레임의 핵심 객체로 등장함",
     "[gemini-pro] 화면 내에서 읽을 수 있는 글씨를 배제하라는 지침(No readable writing)을 어기고 지폐의 텍스트가 명확히 판독됨",
     "[gpt] 요금통 안에 지정된 두 장을 초과하는 지폐가 있어 여분 소품이 발명되었다.",
     "[gpt] 지정된 원형 아날로그 계기 세 개 대신 다섯 개가 보여 고정 설비가 중복되었다.",
     "[gpt] 지폐와 기둥 요금표의 숫자·문자가 읽혀 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
    ],
    "physics": "동전과 지폐들은 요금통의 바닥면에 안정적으로 놓여 중력의 지지를 받고 있습니다."
   },
   {
    "label": "B",
    "direction": "카메라는 가파른 하향 시점(1인칭)으로 요금통을 통과해 바닥에 놓인 접힌 지폐와 동전들을 정확히 겨냥하고 있습니다.",
    "built_space": "버스 내부로 배경에 복도와 승객용 좌석들이 보입니다. 요금통이 기둥에 쇠사슬로 연결되어 있으나, 레퍼런스와 달리 요금통 전체가 투명한 재질로 묘사되었습니다.",
    "entities": "투명한 요금통, 쇠사슬, 100원짜리 동전들, 그리고 심하게 접힌 두 장의 1,000원권 지폐가 존재합니다. 텍스트는 대체로 찌그러져 판독하기 어렵게 처리되었습니다.",
    "hard_violations": [
     "[gpt] 지폐의 액면 숫자와 문자가 읽힐 정도로 선명해 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
    ],
    "physics": "동전과 접힌 지폐들은 요금통의 투명한 바닥면 위에 자연스럽게 흩어져 지지받고 있습니다."
   }
  ],
  "cross_model_order": {
   "policy": "cross_model_order_v2_slot0_fwd_slot1_rev_parallel2",
   "slots": [
    {
     "model": "gemini-pro",
     "order": "forward",
     "display_to_canonical": {
      "A": "A",
      "B": "B"
     },
     "raw": {
      "winner": "B",
      "ranking": [
       "B",
       "A"
      ],
      "verdicts": [
       {
        "label": "B",
        "score": 8,
        "verdict_ko": "지시된 가파른 하향 시점과 두 장의 접힌 천원권 지폐를 성공적으로 구현했으나, 요금통의 측면 재질이 레퍼런스(금속)와 달리 투명하게 표현된 점이 아쉽습니다."
       },
       {
        "label": "A",
        "score": 3,
        "verdict_ko": "요금통의 형태는 레퍼런스와 유사하나, 프롬프트에 없는 만원권이 등장하고 지폐가 접혀 있지 않으며, 읽을 수 없는 텍스트 지침을 어기고 글씨가 선명하게 노출되었습니다."
       }
      ],
      "readings": [
       {
        "label": "A",
        "direction": "카메라는 요금통의 투명한 윗면을 통해 얕은 하향 각도로 바닥에 놓인 동전과 지폐들을 향하고 있습니다.",
        "built_space": "버스 내부로 배경에 운전석의 스티어링 휠과 계기판이 보입니다. 요금통은 레퍼런스와 일치하는 금속 본체와 투명한 윗면을 가지고 있으며 기둥에 묶여 있습니다.",
        "entities": "투명한 윗면을 가진 요금통, 쇠사슬, 100원짜리 동전들이 보입니다. 그러나 접힌 두 장의 1,000원권 대신, 펴져 있는 1,000원권 한 장과 10,000원권 한 장이 있으며 표면의 한글과 숫자가 매우 선명하게 읽힙니다.",
        "hard_violations": [
         "프롬프트에서 요구하지 않은 발명된 사물(10,000원권 지폐)이 프레임의 핵심 객체로 등장함",
         "화면 내에서 읽을 수 있는 글씨를 배제하라는 지침(No readable writing)을 어기고 지폐의 텍스트가 명확히 판독됨"
        ],
        "physics": "동전과 지폐들은 요금통의 바닥면에 안정적으로 놓여 중력의 지지를 받고 있습니다."
       },
       {
        "label": "B",
        "direction": "카메라는 가파른 하향 시점(1인칭)으로 요금통을 통과해 바닥에 놓인 접힌 지폐와 동전들을 정확히 겨냥하고 있습니다.",
        "built_space": "버스 내부로 배경에 복도와 승객용 좌석들이 보입니다. 요금통이 기둥에 쇠사슬로 연결되어 있으나, 레퍼런스와 달리 요금통 전체가 투명한 재질로 묘사되었습니다.",
        "entities": "투명한 요금통, 쇠사슬, 100원짜리 동전들, 그리고 심하게 접힌 두 장의 1,000원권 지폐가 존재합니다. 텍스트는 대체로 찌그러져 판독하기 어렵게 처리되었습니다.",
        "hard_violations": [],
        "physics": "동전과 접힌 지폐들은 요금통의 투명한 바닥면 위에 자연스럽게 흩어져 지지받고 있습니다."
       }
      ],
      "all_candidates_fail": false
     },
     "normalized": {
      "winner": "B",
      "ranking": [
       "B",
       "A"
      ],
      "verdicts": [
       {
        "label": "B",
        "score": 8,
        "verdict_ko": "지시된 가파른 하향 시점과 두 장의 접힌 천원권 지폐를 성공적으로 구현했으나, 요금통의 측면 재질이 레퍼런스(금속)와 달리 투명하게 표현된 점이 아쉽습니다."
       },
       {
        "label": "A",
        "score": 3,
        "verdict_ko": "요금통의 형태는 레퍼런스와 유사하나, 프롬프트에 없는 만원권이 등장하고 지폐가 접혀 있지 않으며, 읽을 수 없는 텍스트 지침을 어기고 글씨가 선명하게 노출되었습니다."
       }
      ],
      "all_candidates_fail": false,
      "readings": [
       {
        "label": "A",
        "direction": "카메라는 요금통의 투명한 윗면을 통해 얕은 하향 각도로 바닥에 놓인 동전과 지폐들을 향하고 있습니다.",
        "built_space": "버스 내부로 배경에 운전석의 스티어링 휠과 계기판이 보입니다. 요금통은 레퍼런스와 일치하는 금속 본체와 투명한 윗면을 가지고 있으며 기둥에 묶여 있습니다.",
        "entities": "투명한 윗면을 가진 요금통, 쇠사슬, 100원짜리 동전들이 보입니다. 그러나 접힌 두 장의 1,000원권 대신, 펴져 있는 1,000원권 한 장과 10,000원권 한 장이 있으며 표면의 한글과 숫자가 매우 선명하게 읽힙니다.",
        "hard_violations": [
         "프롬프트에서 요구하지 않은 발명된 사물(10,000원권 지폐)이 프레임의 핵심 객체로 등장함",
         "화면 내에서 읽을 수 있는 글씨를 배제하라는 지침(No readable writing)을 어기고 지폐의 텍스트가 명확히 판독됨"
        ],
        "physics": "동전과 지폐들은 요금통의 바닥면에 안정적으로 놓여 중력의 지지를 받고 있습니다."
       },
       {
        "label": "B",
        "direction": "카메라는 가파른 하향 시점(1인칭)으로 요금통을 통과해 바닥에 놓인 접힌 지폐와 동전들을 정확히 겨냥하고 있습니다.",
        "built_space": "버스 내부로 배경에 복도와 승객용 좌석들이 보입니다. 요금통이 기둥에 쇠사슬로 연결되어 있으나, 레퍼런스와 달리 요금통 전체가 투명한 재질로 묘사되었습니다.",
        "entities": "투명한 요금통, 쇠사슬, 100원짜리 동전들, 그리고 심하게 접힌 두 장의 1,000원권 지폐가 존재합니다. 텍스트는 대체로 찌그러져 판독하기 어렵게 처리되었습니다.",
        "hard_violations": [],
        "physics": "동전과 접힌 지폐들은 요금통의 투명한 바닥면 위에 자연스럽게 흩어져 지지받고 있습니다."
       }
      ]
     },
     "ok": true
    },
    {
     "model": "gpt",
     "order": "reverse",
     "display_to_canonical": {
      "A": "B",
      "B": "A"
     },
     "raw": {
      "winner": "A",
      "ranking": [
       "A",
       "B"
      ],
      "verdicts": [
       {
        "label": "A",
        "score": 6,
        "verdict_ko": "급경사 1인칭 클로즈업, 하단 중앙의 동전과 정확히 두 장인 접힌 천원권, 주변 체인이 핵심 구도를 가장 충실히 구현했지만 지폐의 숫자와 문자가 읽혀 금지 조건을 위반한다."
       },
       {
        "label": "B",
        "score": 2,
        "verdict_ko": "요금통과 돈을 내려다보지만 프레임이 지나치게 넓고 지폐가 두 장보다 많으며 계기판도 지정된 세 개가 아닌 다섯 개가 보여, 핵심 수량·구도·고정 설비 조건을 위반한다."
       }
      ],
      "readings": [
       {
        "label": "A",
        "direction": "카메라는 투명한 요금통 윗면을 통해 가파르게 아래를 향하며, 시선은 하단 중앙 바닥의 접힌 지폐 두 장과 그 주위의 동전들에 정확히 닿는다. 무기나 다른 지시 물체, 사람의 시선은 없다.",
        "built_space": "낡은 버스 전방의 좁은 공간이 배경에 일부 보이며, 투명 요금통 하나가 화면 대부분을 차지한다. 기둥 하나를 감싼 짧은 체인이 화면 가장자리 쪽 고정부로 이어지고, 좌석과 통로는 흐릿한 주변 정보로만 남는다. 계기판은 올바른 클로즈업 때문에 제외되어 있으며 중복 설비나 불가능한 반사는 보이지 않는다.",
        "entities": "사람은 없다. 투명하고 마모된 요금통, 기둥과 연결된 체인, 바닥에 놓인 여러 개의 100원 동전, 접힌 한국 천원권 두 장이 보인다. 지폐 수량과 종류는 맞지만 표면의 ‘1000’ 및 일부 문자가 식별 가능하다.",
        "hard_violations": [
         "지폐의 액면 숫자와 문자가 읽힐 정도로 선명해 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
        ],
        "physics": "동전과 지폐는 모두 요금통의 평평한 바닥에 놓여 지지된다. 요금통은 고정 설비로 서 있고 체인이 기둥과 고정부에 걸려 있다. 떠 있거나 손이 필요한 물체는 없다."
       },
       {
        "label": "B",
        "direction": "카메라는 요금통 안쪽을 비스듬히 내려다보고 시선은 아래쪽의 지폐와 동전들에 닿는다. 다만 급경사 클로즈업의 초점이 돈에 집중되기보다 운전대·계기판·기둥까지 넓게 분산된다.",
        "built_space": "버스 전방에 요금통 하나, 운전대 하나, 기둥 하나와 이를 감싼 체인, 계기판이 보인다. 계기판에는 원형 계기가 다섯 개 보여 지속 상태의 세 개와 맞지 않는다. 기둥의 요금표와 차체 표지가 읽히며, 요금통 윗면에는 창문 반사가 있으나 카메라와 창의 위치상 가능한 반사로 보인다.",
        "entities": "사람은 없다. 투명 요금통과 체인, 여러 100원 동전은 맞지만 지폐는 중앙의 보라색 천원권 외에 주황색 지폐와 오른쪽의 녹색 지폐 등 두 장을 초과해 보인다. 지폐 액면 숫자와 기둥 요금표 문자도 명확히 읽힌다.",
        "hard_violations": [
         "요금통 안에 지정된 두 장을 초과하는 지폐가 있어 여분 소품이 발명되었다.",
         "지정된 원형 아날로그 계기 세 개 대신 다섯 개가 보여 고정 설비가 중복되었다.",
         "지폐와 기둥 요금표의 숫자·문자가 읽혀 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
        ],
        "physics": "동전과 대부분의 지폐는 요금통 바닥이나 서로의 위에 놓여 지지된다. 오른쪽에 세워진 지폐도 통의 바닥과 벽에 기대어 있다. 요금통과 체인은 기둥 및 고정부에 연결되어 있으며, 공중에 뜬 물체는 없다."
       }
      ],
      "all_candidates_fail": true
     },
     "normalized": {
      "winner": "B",
      "ranking": [
       "B",
       "A"
      ],
      "verdicts": [
       {
        "label": "B",
        "score": 6,
        "verdict_ko": "급경사 1인칭 클로즈업, 하단 중앙의 동전과 정확히 두 장인 접힌 천원권, 주변 체인이 핵심 구도를 가장 충실히 구현했지만 지폐의 숫자와 문자가 읽혀 금지 조건을 위반한다."
       },
       {
        "label": "A",
        "score": 2,
        "verdict_ko": "요금통과 돈을 내려다보지만 프레임이 지나치게 넓고 지폐가 두 장보다 많으며 계기판도 지정된 세 개가 아닌 다섯 개가 보여, 핵심 수량·구도·고정 설비 조건을 위반한다."
       }
      ],
      "all_candidates_fail": true,
      "readings": [
       {
        "label": "B",
        "direction": "카메라는 투명한 요금통 윗면을 통해 가파르게 아래를 향하며, 시선은 하단 중앙 바닥의 접힌 지폐 두 장과 그 주위의 동전들에 정확히 닿는다. 무기나 다른 지시 물체, 사람의 시선은 없다.",
        "built_space": "낡은 버스 전방의 좁은 공간이 배경에 일부 보이며, 투명 요금통 하나가 화면 대부분을 차지한다. 기둥 하나를 감싼 짧은 체인이 화면 가장자리 쪽 고정부로 이어지고, 좌석과 통로는 흐릿한 주변 정보로만 남는다. 계기판은 올바른 클로즈업 때문에 제외되어 있으며 중복 설비나 불가능한 반사는 보이지 않는다.",
        "entities": "사람은 없다. 투명하고 마모된 요금통, 기둥과 연결된 체인, 바닥에 놓인 여러 개의 100원 동전, 접힌 한국 천원권 두 장이 보인다. 지폐 수량과 종류는 맞지만 표면의 ‘1000’ 및 일부 문자가 식별 가능하다.",
        "hard_violations": [
         "지폐의 액면 숫자와 문자가 읽힐 정도로 선명해 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
        ],
        "physics": "동전과 지폐는 모두 요금통의 평평한 바닥에 놓여 지지된다. 요금통은 고정 설비로 서 있고 체인이 기둥과 고정부에 걸려 있다. 떠 있거나 손이 필요한 물체는 없다."
       },
       {
        "label": "A",
        "direction": "카메라는 요금통 안쪽을 비스듬히 내려다보고 시선은 아래쪽의 지폐와 동전들에 닿는다. 다만 급경사 클로즈업의 초점이 돈에 집중되기보다 운전대·계기판·기둥까지 넓게 분산된다.",
        "built_space": "버스 전방에 요금통 하나, 운전대 하나, 기둥 하나와 이를 감싼 체인, 계기판이 보인다. 계기판에는 원형 계기가 다섯 개 보여 지속 상태의 세 개와 맞지 않는다. 기둥의 요금표와 차체 표지가 읽히며, 요금통 윗면에는 창문 반사가 있으나 카메라와 창의 위치상 가능한 반사로 보인다.",
        "entities": "사람은 없다. 투명 요금통과 체인, 여러 100원 동전은 맞지만 지폐는 중앙의 보라색 천원권 외에 주황색 지폐와 오른쪽의 녹색 지폐 등 두 장을 초과해 보인다. 지폐 액면 숫자와 기둥 요금표 문자도 명확히 읽힌다.",
        "hard_violations": [
         "요금통 안에 지정된 두 장을 초과하는 지폐가 있어 여분 소품이 발명되었다.",
         "지정된 원형 아날로그 계기 세 개 대신 다섯 개가 보여 고정 설비가 중복되었다.",
         "지폐와 기둥 요금표의 숫자·문자가 읽혀 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
        ],
        "physics": "동전과 대부분의 지폐는 요금통 바닥이나 서로의 위에 놓여 지지된다. 오른쪽에 세워진 지폐도 통의 바닥과 벽에 기대어 있다. 요금통과 체인은 기둥 및 고정부에 연결되어 있으며, 공중에 뜬 물체는 없다."
       }
      ]
     },
     "ok": true
    }
   ],
   "models": [
    "gemini-pro",
    "gpt"
   ],
   "slot_winner_match": true,
   "slot_winner": {
    "gemini-pro": "B",
    "gpt": "B"
   },
   "route": "cross_slot_agree"
  },
  "dual": {
   "models": [
    "gemini-pro",
    "gpt"
   ],
   "normalized": {
    "A": 0.708,
    "B": 2.0
   },
   "adjusted": {
    "A": 0.458,
    "B": 1.75
   },
   "violations": {
    "A": [
     "[gemini-pro] 프롬프트에서 요구하지 않은 발명된 사물(10,000원권 지폐)이 프레임의 핵심 객체로 등장함",
     "[gemini-pro] 화면 내에서 읽을 수 있는 글씨를 배제하라는 지침(No readable writing)을 어기고 지폐의 텍스트가 명확히 판독됨",
     "[gpt] 요금통 안에 지정된 두 장을 초과하는 지폐가 있어 여분 소품이 발명되었다.",
     "[gpt] 지정된 원형 아날로그 계기 세 개 대신 다섯 개가 보여 고정 설비가 중복되었다.",
     "[gpt] 지폐와 기둥 요금표의 숫자·문자가 읽혀 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
    ],
    "B": [
     "[gpt] 지폐의 액면 숫자와 문자가 읽힐 정도로 선명해 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
    ]
   },
   "per_model_winner": {
    "gemini-pro": "B",
    "gpt": "B"
   },
   "agreed": true
  },
  "totals": {
   "B": 1750,
   "A": 458
  },
  "selected": "B",
  "ranking": [
   "B",
   "A"
  ],
  "verdicts": [
   {
    "label": "B",
    "score": 1750,
    "verdict_ko": "지시된 가파른 하향 시점과 두 장의 접힌 천원권 지폐를 성공적으로 구현했으나, 요금통의 측면 재질이 레퍼런스(금속)와 달리 투명하게 표현된 점이 아쉽습니다.  ★위반: [gpt] 지폐의 액면 숫자와 문자가 읽힐 정도로 선명해 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
   },
   {
    "label": "A",
    "score": 458,
    "verdict_ko": "요금통의 형태는 레퍼런스와 유사하나, 프롬프트에 없는 만원권이 등장하고 지폐가 접혀 있지 않으며, 읽을 수 없는 텍스트 지침을 어기고 글씨가 선명하게 노출되었습니다.  ★위반: [gemini-pro] 프롬프트에서 요구하지 않은 발명된 사물(10,000원권 지폐)이 프레임의 핵심 객체로 등장함 / [gemini-pro] 화면 내에서 읽을 수 있는 글씨를 배제하라는 지침(No readable writing)을 어기고 지폐의 텍스트가 명확히 판독됨 / [gpt] 요금통 안에 지정된 두 장을 초과하는 지폐가 있어 여분 소품이 발명되었다. / [gpt] 지정된 원형 아날로그 계기 세 개 대신 다섯 개가 보여 고정 설비가 중복되었다. / [gpt] 지폐와 기둥 요금표의 숫자·문자가 읽혀 ‘읽을 수 있는 글자 금지’ 조건을 위반한다."
   }
  ],
  "refs": [
   {
    "label": "LOCATION PHOTOGRAPH — the exact place of this shot: its architecture, materials, fixed features and lighting mood are spatial truth; stage the moment inside this place. Never copy its camera framing.",
    "path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.png",
    "asset_id": "9e975568-11df-4493-a43b-8bda7e806e30",
    "role": "location_plate"
   }
  ],
  "critique_skipped": true,
  "shot_run_produced": true,
  "shot_run_uid": "06a928d9-da34-7634-aa50-3896978f5343",
  "ref_mode": "플레이트만 (배경 전용)",
  "share_plan": {
   "ref_plan": "background"
  }
 },
 "S1sh7::cine": {
  "applied": true,
  "attempted_at": "2026-08-29T07:44:52.781724+00:00",
  "fingerprint": "fdbe897271dea2f4dfbaa1e691b05d3c7bbcf98cafa479993bfbdfeffb568b8d",
  "fingerprint_version": 2,
  "provider": "reve",
  "endpoint": "reve/2.1/edit",
  "model": "reve/2.1/edit",
  "pack": "24.202608252115",
  "source_file": "S1sh7_sel.png",
  "source_sha256": "ac0a2573c2ebbacf938dcb46c399247aa87ea89da03210314136bba94328a9c8",
  "file": "S1sh7_cine.png",
  "staged_sha256": "22ec2cc448e13a301ca341ebe4cff554d385c290b71f5ca0e65d56ccdf71a1e9",
  "latency_ms": 84692,
  "request_id": "01a04c7a-8f3e-77c1-a41f-b9b18a9a29bf",
  "status_url": "https://queue.fal.run/reve/2.1/requests/01a04c7a-8f3e-77c1-a41f-b9b18a9a29bf/status",
  "response_url": "https://queue.fal.run/reve/2.1/requests/01a04c7a-8f3e-77c1-a41f-b9b18a9a29bf",
  "submitted_at": "2026-08-29T07:44:55.673630+00:00"
 },
 "S1sh9::confined_fp_apt": {
  "applies": true,
  "reason_ko": "버스 내부 앞문, 요금통, 운전석 등 특정 구조물들의 정확한 위치와 인물(요금통 앞의 정임, 앞문의 최씨) 간의 공간적 배치 및 시선 방향이 샷의 핵심이므로 평면도 형태의 레이아웃 보조가 필요합니다.",
  "input_fingerprint": "2449ad0105028014"
 },
 "S2sh5::confined_fp_apt": {
  "applies": true,
  "reason_ko": "버스 내부라는 제한된 공간에서 통로, 운전석, 그리고 그 옆의 빈 받침대라는 구체적인 위치 관계와 인물의 시선 방향이 정확히 연출되어야 하므로 평면도 보조가 유용합니다.",
  "input_fingerprint": "b8cb96be7686de4e"
 },
 "S3sh5::confined_fp_apt": {
  "applies": false,
  "reason_ko": "이 샷은 정임의 손바닥 위에 놓인 회수권 뭉치를 보여주는 클로즈업 샷입니다. 배경이 버스 내부이기는 하지만 화면에 좌석이나 조작부의 배치가 나타나지 않으며 공간적 인접성이 중요하게 작용하지 않으므로 평면도 레이아웃 보조가 필요하지 않습니다.",
  "input_fingerprint": "3bcdd2fa279c4468"
 },
 "S3sh5::signage": {
  "fp": "da9f311542f29d65",
  "inscriptions": [],
  "cues": [
   {
    "text_native": "",
    "source": "scene_text_implied",
    "source_quote": "낡은 회수권 뭉치"
   }
  ],
  "dropped": []
 },
 "era_assess::c6e56acada22c2ca": {
  "subjects": [
   {
    "subject_native": "1980년대 한국 시외버스 내부 및 운전석",
    "search_terms_native": [
     "1980년대 시외버스 내부",
     "80년대 버스 내부 운전석",
     "옛날 시외버스 실내 요금통"
    ],
    "language_lock_native": "반드시 한국어로만 검색해야 하며, 다른 언어로 번역하거나 영문 검색어를 추가하지 마십시오.",
    "reason_ko": "1980년대 한국 버스의 특유한 아날로그 계기판, 요금통 형태, 비닐 시트 구조는 현대 버스와 달라 고증 자료가 필요함."
   }
  ],
  "subject_text": "차고지에 세워진 낡은 시외버스 1호차 내부\n낡은 비닐 좌석 커버와 고무 통로 매트가 있는 1980년대 시외버스 내부. 전면에는 둥근 아날로그 계기 세 개와 요금통이 있다.",
  "identity": "canonical",
  "scope_id": "L01",
  "scope_role": "location_interior",
  "scope_sha": "fdd4a07884b416d4"
 },
 "era_ref::a731040c08289977": {
  "subject": "1980년대 한국 시외버스 내부 및 운전석",
  "terms": [
   "1980년대 시외버스 내부",
   "80년대 버스 내부 운전석",
   "옛날 시외버스 실내 요금통"
  ],
  "queries": [
   [
    "1980년대 한국 시외버스 내부 운전석 요금통",
    "80년대 옛날 시외버스 실내 운전석 요금통"
   ]
  ],
  "candidates": 4,
  "picked_index": 3,
  "picked_url": "https://i1.ruliweb.com/img/18/07/04/164643f06bf11ca25.png",
  "picked_reason_ko": "1980년대 프론트엔진 버스의 운전석과 출입문 주변 구조가 가장 사실적이고 명확하게 드러나며, 당시 사용되던 비즈 방석이나 안내문 등 일상적인 디테일이 훌륭한 레퍼런스를 제공합니다.",
  "verdicts": [
   {
    "index": 1,
    "usable": true,
    "score": 85,
    "reason_ko": "구조는 명확하게 보이나 다소 복원된 박물관 전시품 같은 느낌을 줍니다."
   },
   {
    "index": 2,
    "usable": true,
    "score": 35,
    "reason_ko": "승객석 일부만 확인되며 핵심인 운전석과 전체 내부 구조를 파악할 수 없습니다."
   },
   {
    "index": 3,
    "usable": true,
    "score": 92,
    "reason_ko": "운전석, 엔진룸 덮개, 출입문 구조뿐만 아니라 당시의 생활감 있는 디테일이 매우 선명하게 나타납니다."
   },
   {
    "index": 4,
    "usable": false,
    "score": 0,
    "reason_ko": "버스 내부 구조가 아닌 요금함 소품만 보여주므로 사용할 수 없습니다."
   }
  ],
  "candidate_urls": [
   "https://file1.bobaedream.co.kr/multi_image/truck/2020/01/15/19/CQA5e1eee56bb76d.jpg",
   "https://p1-tt.byteimg.com/origin/pgc-image/838657bcf83a4368a08b391f0c3de828.jpg",
   "https://i1.ruliweb.com/img/18/07/04/164643f06bf11ca25.png",
   "https://silversbh.daup7.com/v/durdmagka1.jpg"
  ],
  "sha256": "4c5399991bcddf597f5484363eebb0adc3d12003375778c84d7e1625f5cbbd01",
  "file": "eraref_a731040c08289977.png"
 },
 "S3sh5::bgfirst_bg": {
  "input_fingerprint": "3820c0924c1fe5b3",
  "prompt": "Create the EMPTY BACKGROUND PLATE for one film shot — NO PEOPLE, no figures, no body parts, no sketch lines, no arrows anywhere.\n\"Empty\" means no people only: KEEP the location's inherent occupants and stock that define the place — animals in an animal shelter, pen or farm, goods in a market, moored boats in a harbour — unless the shot text explicitly removes them.\nThe FIRST attached image is a thin-line storyboard sketch: use ONLY its camera angle, horizon, perspective and the placement/size of buildings and set masses — ignore the sketched people and arrows entirely. The SECOND attached image (LOCATION PHOTOGRAPH) is the real place: take its architecture, materials, signage and fixed features, and RE-PROJECT them into the sketch's camera. If the photograph's camera differs from the sketch's, the sketch's camera wins.\nHUMAN-SCALE CALIBRATION: derive every structure's true size from human-scale elements — a door ≈ 2m, a window ≈ 1–1.5m wide, one storey ≈ 2.5–3m; never inflate a small structure or shrink a large one.\n\nSHOT TEXT this background must serve (Korean): 정임의 쫙 펴진 손바닥 위에 고무줄로 묶인 낡은 회수권 뭉치가 평평하게 놓인 클로즈업.\n\nLOCATION (lock): Inside the aging intercity bus’s front seating area, beside the seat directly behind the driver’s position. The windows look out into full darkness.\n\nTIME OF DAY (lock): night.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: rubber-banded used ticket bundle in the middle-center of the frame, foreground; 정임's open hand in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: used ticket bundle (old, bound with a rubber band, with its cover folded) — The folded cover and layered paper edges face upward toward the oblique camera while the complete bundle lies flat across the palm; used as Primary insert detail centered on the hand without exceeding the hand's visible scale; rubber band (wrapped around the ticket bundle); used as Visually contains the old tickets and identifies the recovered bundle; edge of the seat behind the driver's position (seat back still fitted with its old vinyl cover) — A small oblique portion of the seat edge remains beyond the hand; used as Provides environmental and scale context without competing with the ticket bundle.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient illumination appropriate to the night bus interior uses muted aged neutrals and restrained contrast, with the paper edges held legibly against 정임's palm.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nRender ONE photorealistic empty location photograph, 16:9, that this shot can be staged inside later. No readable writing anywhere: surfaces that would carry writing may be present, but stage any wording out of legibility — an oblique angle, distance, shallow focus. No captions, watermarks or overlay text.\n\nPERIOD REFERENCE — 1980년대 한국 시외버스 내부 및 운전석: a researched photograph of the real\nthing. Copy its era-accurate form, proportions, materials, fittings\nand styling exactly. It decides ONLY what this thing looks like —\nnever the composition, framing, lighting, people or their placement.",
  "effective_prompt": "Create the EMPTY BACKGROUND PLATE for one film shot — NO PEOPLE, no figures, no body parts, no sketch lines, no arrows anywhere.\n\"Empty\" means no people only: KEEP the location's inherent occupants and stock that define the place — animals in an animal shelter, pen or farm, goods in a market, moored boats in a harbour — unless the shot text explicitly removes them.\nThe FIRST attached image is a thin-line storyboard sketch: use ONLY its camera angle, horizon, perspective and the placement/size of buildings and set masses — ignore the sketched people and arrows entirely. The SECOND attached image (LOCATION PHOTOGRAPH) is the real place: take its architecture, materials, signage and fixed features, and RE-PROJECT them into the sketch's camera. If the photograph's camera differs from the sketch's, the sketch's camera wins.\nHUMAN-SCALE CALIBRATION: derive every structure's true size from human-scale elements — a door ≈ 2m, a window ≈ 1–1.5m wide, one storey ≈ 2.5–3m; never inflate a small structure or shrink a large one.\n\nSHOT TEXT this background must serve (Korean): 정임의 쫙 펴진 손바닥 위에 고무줄로 묶인 낡은 회수권 뭉치가 평평하게 놓인 클로즈업.\n\nLOCATION (lock): Inside the aging intercity bus’s front seating area, beside the seat directly behind the driver’s position. The windows look out into full darkness.\n\nTIME OF DAY (lock): night.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: rubber-banded used ticket bundle in the middle-center of the frame, foreground; 정임's open hand in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: used ticket bundle (old, bound with a rubber band, with its cover folded) — The folded cover and layered paper edges face upward toward the oblique camera while the complete bundle lies flat across the palm; used as Primary insert detail centered on the hand without exceeding the hand's visible scale; rubber band (wrapped around the ticket bundle); used as Visually contains the old tickets and identifies the recovered bundle; edge of the seat behind the driver's position (seat back still fitted with its old vinyl cover) — A small oblique portion of the seat edge remains beyond the hand; used as Provides environmental and scale context without competing with the ticket bundle.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient illumination appropriate to the night bus interior uses muted aged neutrals and restrained contrast, with the paper edges held legibly against 정임's palm.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nRender ONE photorealistic empty location photograph, 16:9, that this shot can be staged inside later. No readable writing anywhere: surfaces that would carry writing may be present, but stage any wording out of legibility — an oblique angle, distance, shallow focus. No captions, watermarks or overlay text.\n\nPERIOD REFERENCE — 1980년대 한국 시외버스 내부 및 운전석: a researched photograph of the real\nthing. Copy its era-accurate form, proportions, materials, fittings\nand styling exactly. It decides ONLY what this thing looks like —\nnever the composition, framing, lighting, people or their placement.",
  "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/scene/recipe/S3sh5__bgfirst_bg.png",
  "asset_id": "bd974e7a-805b-4177-b546-9163b0ef8099",
  "input_asset_ids": [
   "a52d59e5-718e-4413-8820-08655d495ba1",
   "9e975568-11df-4493-a43b-8bda7e806e30"
  ],
  "era_research": {
   "subject": "1980년대 한국 시외버스 내부 및 운전석",
   "queries": [
    [
     "1980년대 한국 시외버스 내부 운전석 요금통",
     "80년대 옛날 시외버스 실내 운전석 요금통"
    ]
   ],
   "picked_url": "https://i1.ruliweb.com/img/18/07/04/164643f06bf11ca25.png",
   "sha256": "4c5399991bcddf597f5484363eebb0adc3d12003375778c84d7e1625f5cbbd01",
   "file": "eraref_a731040c08289977.png"
  }
 },
 "S3sh5": {
  "input_fingerprint": "d39bb68a670fc4e1",
  "prompt": "Create ONE FINAL photorealistic live-action film still of the moment below — late 1970s–1980s South Korea; all people are Korean unless stated. TIME OF DAY (lock): night.\n\nSHOT TEXT (authoritative, Korean): 정임의 쫙 펴진 손바닥 위에 고무줄로 묶인 낡은 회수권 뭉치가 평평하게 놓인 클로즈업.\n\nLOCATION (lock): Inside the aging intercity bus’s front seating area, beside the seat directly behind the driver’s position. The windows look out into full darkness. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: rubber-banded used ticket bundle in the middle-center of the frame, foreground; 정임's open hand in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: used ticket bundle (old, bound with a rubber band, with its cover folded) — The folded cover and layered paper edges face upward toward the oblique camera while the complete bundle lies flat across the palm; used as Primary insert detail centered on the hand without exceeding the hand's visible scale; rubber band (wrapped around the ticket bundle); used as Visually contains the old tickets and identifies the recovered bundle; edge of the seat behind the driver's position (seat back still fitted with its old vinyl cover) — A small oblique portion of the seat edge remains beyond the hand; used as Provides environmental and scale context without competing with the ticket bundle.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient illumination appropriate to the night bus interior uses muted aged neutrals and restrained contrast, with the paper edges held legibly against 정임's palm.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nREALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot\ntext may describe characters metaphorically, figuratively or with\nexaggeration. Photograph what a real movie camera would actually\nrecord on a physical set — exaggerated or figurative impressions\nbecome realistic staging within whatever this brief already fixes,\nnot literal fantasy imagery.\n\nEVERY CHARACTER IS A HUMAN BEING: unless the story explicitly\nfeatures non-human or virtual beings (as in science fiction or\nfantasy), every character — however indirectly, vaguely or\nfiguratively the text describes them — IS a real human. When the\ntext gives no direct visual description of a person it puts in\nthis shot, imagine that description and still show them as a\nconcrete, fully-formed human being:\nrender the human form as fully as the framing shows — never reduce\na person to a shape, blob, solid silhouette or abstract mass.\n\nEXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a\nperson's eyes, face or presence emotionally or figuratively (vacant,\nhollow, dazed, burning, lifeless gaze and the like), it describes an\nACTOR'S PERFORMANCE captured by a real camera — realize it ONLY\nthrough gaze direction, focus, eyelids, facial muscles, stillness\nand posture. Every living person's eyes remain anatomically normal\nhuman eyes with a natural iris and pupil, natural sclera and normal\nproportions; NEVER whiten, blank out, cloud over, glow, enlarge or\notherwise alter eyeballs, skin or anatomy — unless the story\nexplicitly declares that being non-human or supernatural in form.\n\nPROPS FACE THE RIGHT WAY: every handheld or used object must be\noriented exactly as its real-world use requires. A person reading,\nwatching or operating something (a phone, a photograph, a paper,\nany device) has its functional side — screen, front, page — facing\nTHEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract, immobility contract or shot-text\ndirection says otherwise, people read as alive in mid-moment —\nbelievable weight shift, hands naturally positioned for the action\nthe SHOT TEXT already gives them, gaze on the target the SHOT TEXT\nimplies; avoid a stiff attention stance (feet together, arms hanging\nstraight down) and a blank stare into the lens. If the SHOT TEXT or\nany POSE/IMMOBILE contract above stages stillness, death, sleep,\nunconsciousness, restraint, drill or an explicit direct-to-camera\nlook, follow THAT exactly — this clause never overrides it.\n\nDRAWN MARKS KEEP THEIR SHAPE: any mark the text describes as drawn,\npainted or traced (a circle, a line, a symbol) is a STROKE sitting on\nthe surface — an outline whose interior still shows the underlying\nsurface (wall, skin, paper). Render its stated shape faithfully: a\ndrawn circle stays an open ring of brush-width, never filled into a\nsolid disc, unless the text explicitly says it is filled.\n\nBODY & SUPPORT (default only — every explicit direction above wins): a body relates to what holds it. A seated person sits the way the seat is built to be used — hips on the seat, back toward the backrest, legs falling naturally toward the floor; people sharing adjacent seats each occupy their own seat, side by side. Hands, hips and feet keep believable contact with whatever they rest on. When the text stages someone frozen, stunned or holding still, the body stops mid-action exactly where the moment caught it — weight already committed to one side, hands where the interrupted movement left them — rather than resetting into a symmetric at-attention stance. If the SHOT TEXT or any contract above stages a specific arrangement, follow THAT exactly.\n\nCARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Bus No. 1 still has its old vinyl seatback covers, rubber aisle mat, and chained fare box in the same position; the coins and two folded bills remain inside. The windows are dark with night outside. 정임: She wears her navy conductor's uniform and brimmed cap and stands near the fare box. A worn bundle of tickets bound with a rubber band lies flat on her open palm.\n\nTHE HAND THAT IS DOING THIS: the object at the centre of this shot is being held, operated, read, aimed or handed over by 정임 right now, so 정임's hand — and as much of the wrist and forearm as the framing reaches — is in the frame, gripping or resting on that object exactly the way its real use requires. Match that hand to 정임: its size, build, skin, age, grooming, sleeve and anything worn on it belong to that person and to no one else.\n\nPEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정임 (한국인 여성, 20대의 젊은 얼굴, 자연스러운 짙은색 머리, 구체적인 얼굴형과 헤어스타일은 미상) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above.\n\nCHARACTER REFERENCE ROLE (follow exactly): the attached CHARACTER REFERENCE images establish identity only — face, hair, build and clothing. The pose, gaze direction, camera angle and framing inside those reference images belong to the reference photos, not to this shot; never copy them. Pose and gaze in this shot follow only the CAMERA and action text of this prompt. When this prompt stages a character's face as covered or hidden — by a costume head, mask, helmet, hood, or a body turned away — that staging wins: keep the covering exactly as described and never pull the reference face into view from under it; the reference then guides only what stays visible, such as build and clothing.\n\nNo readable writing anywhere in this image. Surfaces that would carry writing may be present, but nothing a viewer could read: stage every one of them out of legibility — a hand across, an oblique angle, shallow focus, or simply turned away. No caption, subtitle, watermark, logo or overlay.",
  "roll_prompts": {
   "A": "Stage the shot inside a tight, built interior. The FIRST attached image (SHOT BACKGROUND) is the finished empty interior of this shot, and in a space this cramped its geometry is the truth of the shot — keep it EXACTLY: its camera, perspective and every fixed fitting it has stay untouched, in the same place, at the same angle, in the same number.\n\nBefore you place anyone, count what the background shows: every fixed fitting this space has, how many of each, which way each faces, and what any reflective surface among them could return from this camera. Those counts and placements are what you must still be able to make after the people are in. Adding a second one of anything, moving a fitting or growing a new surface is a failure even when the person looks right.\n\nThe SECOND attached image (LAYOUT SKETCH) tells you where the people go: each sketched person's position, screen size, pose and the gaze/motion arrows. Its background lines are not decoration — they are the same structure seen in line form, so use them to place each person correctly with respect to it: where the body rests and on what, which side of a fitting the hands are on, what the body passes in front of and what it passes behind. Where sketch and background disagree about the structure itself, the background wins.\n\nThe CHARACTER REFERENCE photographs show the real people.\n\nPlace the real people into the background at exactly the sketched positions, sizes and poses, following the arrow directions. A person may cover part of the structure — that is expected, and covering is not redrawing. What the body hides stays hidden; what remains visible stays exactly as the background had it. No sketch lines or arrows may remain.\n\nCreate ONE FINAL photorealistic live-action film still of the moment below — late 1970s–1980s South Korea; all people are Korean unless stated. TIME OF DAY (lock): night.\n\nSHOT TEXT (authoritative, Korean): 정임의 쫙 펴진 손바닥 위에 고무줄로 묶인 낡은 회수권 뭉치가 평평하게 놓인 클로즈업.\n\nLOCATION (lock): Inside the aging intercity bus’s front seating area, beside the seat directly behind the driver’s position. The windows look out into full darkness. The shot takes place here — the FIRST attached image (SHOT BACKGROUND) is this exact place, already built: its ground, structures, horizon, materials and lighting are the finished truth of this location and must not be redesigned or replaced. No location photograph is attached — read the place from that image alone, and add no scenery, structure, vehicle or fixture that it does not already show. This lock governs the place only; the figures in the shot follow the staging and pose instructions.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: rubber-banded used ticket bundle in the middle-center of the frame, foreground; 정임's open hand in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: used ticket bundle (old, bound with a rubber band, with its cover folded) — The folded cover and layered paper edges face upward toward the oblique camera while the complete bundle lies flat across the palm; used as Primary insert detail centered on the hand without exceeding the hand's visible scale; rubber band (wrapped around the ticket bundle); used as Visually contains the old tickets and identifies the recovered bundle; edge of the seat behind the driver's position (seat back still fitted with its old vinyl cover) — A small oblique portion of the seat edge remains beyond the hand; used as Provides environmental and scale context without competing with the ticket bundle.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient illumination appropriate to the night bus interior uses muted aged neutrals and restrained contrast, with the paper edges held legibly against 정임's palm.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nREALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot\ntext may describe characters metaphorically, figuratively or with\nexaggeration. Photograph what a real movie camera would actually\nrecord on a physical set — exaggerated or figurative impressions\nbecome realistic staging within whatever this brief already fixes,\nnot literal fantasy imagery.\n\nEVERY CHARACTER IS A HUMAN BEING: unless the story explicitly\nfeatures non-human or virtual beings (as in science fiction or\nfantasy), every character — however indirectly, vaguely or\nfiguratively the text describes them — IS a real human. When the\ntext gives no direct visual description of a person it puts in\nthis shot, imagine that description and still show them as a\nconcrete, fully-formed human being:\nrender the human form as fully as the framing shows — never reduce\na person to a shape, blob, solid silhouette or abstract mass.\n\nEXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a\nperson's eyes, face or presence emotionally or figuratively (vacant,\nhollow, dazed, burning, lifeless gaze and the like), it describes an\nACTOR'S PERFORMANCE captured by a real camera — realize it ONLY\nthrough gaze direction, focus, eyelids, facial muscles, stillness\nand posture. Every living person's eyes remain anatomically normal\nhuman eyes with a natural iris and pupil, natural sclera and normal\nproportions; NEVER whiten, blank out, cloud over, glow, enlarge or\notherwise alter eyeballs, skin or anatomy — unless the story\nexplicitly declares that being non-human or supernatural in form.\n\nPROPS FACE THE RIGHT WAY: every handheld or used object must be\noriented exactly as its real-world use requires. A person reading,\nwatching or operating something (a phone, a photograph, a paper,\nany device) has its functional side — screen, front, page — facing\nTHEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract, immobility contract or shot-text\ndirection says otherwise, people read as alive in mid-moment —\nbelievable weight shift, hands naturally positioned for the action\nthe SHOT TEXT already gives them, gaze on the target the SHOT TEXT\nimplies; avoid a stiff attention stance (feet together, arms hanging\nstraight down) and a blank stare into the lens. If the SHOT TEXT or\nany POSE/IMMOBILE contract above stages stillness, death, sleep,\nunconsciousness, restraint, drill or an explicit direct-to-camera\nlook, follow THAT exactly — this clause never overrides it.\n\nDRAWN MARKS KEEP THEIR SHAPE: any mark the text describes as drawn,\npainted or traced (a circle, a line, a symbol) is a STROKE sitting on\nthe surface — an outline whose interior still shows the underlying\nsurface (wall, skin, paper). Render its stated shape faithfully: a\ndrawn circle stays an open ring of brush-width, never filled into a\nsolid disc, unless the text explicitly says it is filled.\n\nBODY & SUPPORT (default only — every explicit direction above wins): a body relates to what holds it. A seated person sits the way the seat is built to be used — hips on the seat, back toward the backrest, legs falling naturally toward the floor; people sharing adjacent seats each occupy their own seat, side by side. Hands, hips and feet keep believable contact with whatever they rest on. When the text stages someone frozen, stunned or holding still, the body stops mid-action exactly where the moment caught it — weight already committed to one side, hands where the interrupted movement left them — rather than resetting into a symmetric at-attention stance. If the SHOT TEXT or any contract above stages a specific arrangement, follow THAT exactly.\n\nCARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Bus No. 1 still has its old vinyl seatback covers, rubber aisle mat, and chained fare box in the same position; the coins and two folded bills remain inside. The windows are dark with night outside. 정임: She wears her navy conductor's uniform and brimmed cap and stands near the fare box. A worn bundle of tickets bound with a rubber band lies flat on her open palm.\n\nTHE HAND THAT IS DOING THIS: the object at the centre of this shot is being held, operated, read, aimed or handed over by 정임 right now, so 정임's hand — and as much of the wrist and forearm as the framing reaches — is in the frame, gripping or resting on that object exactly the way its real use requires. Match that hand to 정임: its size, build, skin, age, grooming, sleeve and anything worn on it belong to that person and to no one else.\n\nPEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정임 (한국인 여성, 20대의 젊은 얼굴, 자연스러운 짙은색 머리, 구체적인 얼굴형과 헤어스타일은 미상) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above.\n\nCHARACTER REFERENCE ROLE (follow exactly): the attached CHARACTER REFERENCE images establish identity only — face, hair, build and clothing. The pose, gaze direction, camera angle and framing inside those reference images belong to the reference photos, not to this shot; never copy them. Pose and gaze in this shot follow only the CAMERA and action text of this prompt. When this prompt stages a character's face as covered or hidden — by a costume head, mask, helmet, hood, or a body turned away — that staging wins: keep the covering exactly as described and never pull the reference face into view from under it; the reference then guides only what stays visible, such as build and clothing.\n\nNo readable writing anywhere in this image. Surfaces that would carry writing may be present, but nothing a viewer could read: stage every one of them out of legibility — a hand across, an oblique angle, shallow focus, or simply turned away. No caption, subtitle, watermark, logo or overlay.",
   "B": "Create ONE FINAL photorealistic live-action film still of the moment below — late 1970s–1980s South Korea; all people are Korean unless stated. TIME OF DAY (lock): night.\n\nSHOT TEXT (authoritative, Korean): 정임의 쫙 펴진 손바닥 위에 고무줄로 묶인 낡은 회수권 뭉치가 평평하게 놓인 클로즈업.\n\nLOCATION (lock): Inside the aging intercity bus’s front seating area, beside the seat directly behind the driver’s position. The windows look out into full darkness. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: rubber-banded used ticket bundle in the middle-center of the frame, foreground; 정임's open hand in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: used ticket bundle (old, bound with a rubber band, with its cover folded) — The folded cover and layered paper edges face upward toward the oblique camera while the complete bundle lies flat across the palm; used as Primary insert detail centered on the hand without exceeding the hand's visible scale; rubber band (wrapped around the ticket bundle); used as Visually contains the old tickets and identifies the recovered bundle; edge of the seat behind the driver's position (seat back still fitted with its old vinyl cover) — A small oblique portion of the seat edge remains beyond the hand; used as Provides environmental and scale context without competing with the ticket bundle.\nCompose the frame exactly as specified above — subject scale and screen placement. The viewing angle is deliberately left open here; choose the angle that serves the shot. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nLIGHTING & MOOD (these govern light, color and surface rendering):\n- LIGHTING & MOOD: Subdued ambient illumination appropriate to the night bus interior uses muted aged neutrals and restrained contrast, with the paper edges held legibly against 정임's palm.\n- MATERIAL REALISM: every object and surface must read as a real,\n  physical material — correct texture, weight, wear and light response\n  (metal reflects, fabric drapes and creases, liquid is glossy and\n  pools, painted or drawn marks sit ON a surface and follow its\n  curvature and lighting). Nothing may look like a flat sticker, a\n  doodle or a graphic overlay pasted onto the frame.\n\nREALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot\ntext may describe characters metaphorically, figuratively or with\nexaggeration. Photograph what a real movie camera would actually\nrecord on a physical set — exaggerated or figurative impressions\nbecome realistic staging within whatever this brief already fixes,\nnot literal fantasy imagery.\n\nEVERY CHARACTER IS A HUMAN BEING: unless the story explicitly\nfeatures non-human or virtual beings (as in science fiction or\nfantasy), every character — however indirectly, vaguely or\nfiguratively the text describes them — IS a real human. When the\ntext gives no direct visual description of a person it puts in\nthis shot, imagine that description and still show them as a\nconcrete, fully-formed human being:\nrender the human form as fully as the framing shows — never reduce\na person to a shape, blob, solid silhouette or abstract mass.\n\nEXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a\nperson's eyes, face or presence emotionally or figuratively (vacant,\nhollow, dazed, burning, lifeless gaze and the like), it describes an\nACTOR'S PERFORMANCE captured by a real camera — realize it ONLY\nthrough gaze direction, focus, eyelids, facial muscles, stillness\nand posture. Every living person's eyes remain anatomically normal\nhuman eyes with a natural iris and pupil, natural sclera and normal\nproportions; NEVER whiten, blank out, cloud over, glow, enlarge or\notherwise alter eyeballs, skin or anatomy — unless the story\nexplicitly declares that being non-human or supernatural in form.\n\nPROPS FACE THE RIGHT WAY: every handheld or used object must be\noriented exactly as its real-world use requires. A person reading,\nwatching or operating something (a phone, a photograph, a paper,\nany device) has its functional side — screen, front, page — facing\nTHEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract, immobility contract or shot-text\ndirection says otherwise, people read as alive in mid-moment —\nbelievable weight shift, hands naturally positioned for the action\nthe SHOT TEXT already gives them, gaze on the target the SHOT TEXT\nimplies; avoid a stiff attention stance (feet together, arms hanging\nstraight down) and a blank stare into the lens. If the SHOT TEXT or\nany POSE/IMMOBILE contract above stages stillness, death, sleep,\nunconsciousness, restraint, drill or an explicit direct-to-camera\nlook, follow THAT exactly — this clause never overrides it.\n\nDRAWN MARKS KEEP THEIR SHAPE: any mark the text describes as drawn,\npainted or traced (a circle, a line, a symbol) is a STROKE sitting on\nthe surface — an outline whose interior still shows the underlying\nsurface (wall, skin, paper). Render its stated shape faithfully: a\ndrawn circle stays an open ring of brush-width, never filled into a\nsolid disc, unless the text explicitly says it is filled.\n\nBODY & SUPPORT (default only — every explicit direction above wins): a body relates to what holds it. A seated person sits the way the seat is built to be used — hips on the seat, back toward the backrest, legs falling naturally toward the floor; people sharing adjacent seats each occupy their own seat, side by side. Hands, hips and feet keep believable contact with whatever they rest on. When the text stages someone frozen, stunned or holding still, the body stops mid-action exactly where the moment caught it — weight already committed to one side, hands where the interrupted movement left them — rather than resetting into a symmetric at-attention stance. If the SHOT TEXT or any contract above stages a specific arrangement, follow THAT exactly.\n\nCARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Bus No. 1 still has its old vinyl seatback covers, rubber aisle mat, and chained fare box in the same position; the coins and two folded bills remain inside. The windows are dark with night outside. 정임: She wears her navy conductor's uniform and brimmed cap and stands near the fare box. A worn bundle of tickets bound with a rubber band lies flat on her open palm.\n\nTHE HAND THAT IS DOING THIS: the object at the centre of this shot is being held, operated, read, aimed or handed over by 정임 right now, so 정임's hand — and as much of the wrist and forearm as the framing reaches — is in the frame, gripping or resting on that object exactly the way its real use requires. Match that hand to 정임: its size, build, skin, age, grooming, sleeve and anything worn on it belong to that person and to no one else.\n\nPEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정임 (한국인 여성, 20대의 젊은 얼굴, 자연스러운 짙은색 머리, 구체적인 얼굴형과 헤어스타일은 미상) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above.\n\nCHARACTER REFERENCE ROLE (follow exactly): the attached CHARACTER REFERENCE images establish identity only — face, hair, build and clothing. The pose, gaze direction, camera angle and framing inside those reference images belong to the reference photos, not to this shot; never copy them. Pose and gaze in this shot follow only the CAMERA and action text of this prompt. When this prompt stages a character's face as covered or hidden — by a costume head, mask, helmet, hood, or a body turned away — that staging wins: keep the covering exactly as described and never pull the reference face into view from under it; the reference then guides only what stays visible, such as build and clothing.\n\nNo readable writing anywhere in this image. Surfaces that would carry writing may be present, but nothing a viewer could read: stage every one of them out of legibility — a hand across, an oblique angle, shallow focus, or simply turned away. No caption, subtitle, watermark, logo or overlay.\n\nCOMPOSITION VARIATION (this candidate only): keep the place, the people and the moment exactly as specified, and keep from the CAMERA & FRAME contract its subject scale, screen placement and key background elements exactly. For this candidate only, its camera angle and height are deliberately left open: choose a camera position distinctly different from the obvious one, as a film director picking a second setup on the same blocking. Stay true to any explicit framing the SHOT TEXT itself dictates."
  },
  "roll_refs": {
   "A": [
    {
     "label": "SHOT BACKGROUND",
     "path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/scene/recipe/S3sh5__bgfirst_bg.png",
     "asset_id": "bd974e7a-805b-4177-b546-9163b0ef8099",
     "role": "bgfirst_bg"
    },
    {
     "label": "LAYOUT SKETCH (people placement AND the structure they sit inside — the sketched fixed fittings and openings are the same ones the background photograph shows, drawn as lines; read them to place each body correctly against that structure, and where the two disagree about the structure itself the background photograph wins)",
     "path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/conti/conti_S3sh5.png",
     "asset_id": "a52d59e5-718e-4413-8820-08655d495ba1",
     "role": "conti_light"
    },
    {
     "label": "CHARACTER REFERENCE — 정임: the exact person appearing in this shot; match face, hair and build exactly.",
     "path": "<bytes:1254053>",
     "asset_id": "db331b24-c065-4549-a6ef-681b9e52c8fa",
     "role": "character_ref"
    },
    {
     "label": "PROP REFERENCE — 고무줄로 묶인 낡은 종이 회수권 뭉치: the exact object appearing in this shot; match its look, material and wear exactly.",
     "path": "<bytes:1135067>",
     "asset_id": "6e82ce93-8876-47c1-ac1d-48cf6c9a06d7",
     "role": "prop_ref"
    }
   ],
   "B": [
    {
     "label": "LOCATION PHOTOGRAPH — the exact place of this shot: its architecture, materials, fixed features and lighting mood are spatial truth; stage the moment inside this place. Never copy its camera framing.",
     "path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.png",
     "asset_id": "9e975568-11df-4493-a43b-8bda7e806e30",
     "role": "location_plate"
    },
    {
     "label": "CHARACTER REFERENCE — 정임: the exact person appearing in this shot; match face, hair and build exactly.",
     "path": "<bytes:1254053>",
     "asset_id": "db331b24-c065-4549-a6ef-681b9e52c8fa",
     "role": "character_ref"
    },
    {
     "label": "PROP REFERENCE — 고무줄로 묶인 낡은 종이 회수권 뭉치: the exact object appearing in this shot; match its look, material and wear exactly.",
     "path": "<bytes:1135067>",
     "asset_id": "6e82ce93-8876-47c1-ac1d-48cf6c9a06d7",
     "role": "prop_ref"
    }
   ]
  },
  "shot_run_spend_attempt_count": 1,
  "judge_flip_skipped": "judge_fn_owns_order",
  "readings": [
   {
    "label": "A",
    "direction": "카메라는 쫙 펴진 손바닥과 그 위의 회수권 뭉치를 약간 위쪽에서 비스듬히 내려다보고 있음.",
    "built_space": "버스 내부의 복도와 나열된 빈 좌석들이 배경으로 깊게 보이며, 프롬프트에서 요구한 운전석 바로 뒤 공간의 좁은 느낌보다는 일반적인 버스 복도의 시점이 강함.",
    "entities": "회수권 뭉치와 고무줄은 레퍼런스와 일치하나, 손과 팔 부분에 프롬프트가 요구한 남색 승무원 유니폼 소매가 완전히 누락되어 맨팔이 노출됨.",
    "hard_violations": [
     "[gpt] 회수권 표면의 숫자와 인쇄 표기가 선명하게 읽혀 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
    ],
    "physics": "손바닥이 공중에 떠 있는 상태로 회수권 뭉치를 평평하게 받치고 있음."
   },
   {
    "label": "B",
    "direction": "카메라는 쫙 펴진 손바닥 위에 놓인 회수권 뭉치를 수평에 가까운 앵글로 정면에서 클로즈업하여 바라보고 있음.",
    "built_space": "밤의 어두운 창문과 낡은 비닐 커버가 씌워진 버스 좌석 등받이가 배경에 적절히 배치되어 운전석 뒤쪽 공간임을 잘 보여줌.",
    "entities": "고무줄로 묶인 낡은 회수권 뭉치는 레퍼런스의 질감과 형태를 잘 살렸으며, 손목 부분에 남색 유니폼 소매와 흰색 셔츠 소매 끝이 묘사됨.",
    "hard_violations": [
     "[gpt] 회수권 표면의 숫자와 인쇄 표기가 읽을 수 있는 상태로 노출되어 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
    ],
    "physics": "쫙 펴진 손바닥이 회수권 뭉치를 수평으로 안정감 있게 받치고 있음."
   }
  ],
  "cross_model_order": {
   "policy": "cross_model_order_v2_slot0_fwd_slot1_rev_parallel2",
   "slots": [
    {
     "model": "gemini-pro",
     "order": "forward",
     "display_to_canonical": {
      "A": "A",
      "B": "B"
     },
     "raw": {
      "winner": "B",
      "ranking": [
       "B",
       "A"
      ],
      "verdicts": [
       {
        "label": "B",
        "score": 9,
        "verdict_ko": "지시된 남색 승무원 유니폼 소매를 정확히 반영하였으며, 어두운 창문과 낡은 시트 배경을 통해 프롬프트가 요구한 위치와 분위기를 훌륭하게 구현했습니다."
       },
       {
        "label": "A",
        "score": 5,
        "verdict_ko": "회수권 뭉치의 묘사는 레퍼런스와 유사하나, 인물의 손목에 명시된 남색 유니폼 소매가 누락된 맨팔로 묘사되었고 배경이 지시된 위치의 느낌을 제대로 살리지 못했습니다."
       }
      ],
      "readings": [
       {
        "label": "B",
        "direction": "카메라는 쫙 펴진 손바닥 위에 놓인 회수권 뭉치를 수평에 가까운 앵글로 정면에서 클로즈업하여 바라보고 있음.",
        "built_space": "밤의 어두운 창문과 낡은 비닐 커버가 씌워진 버스 좌석 등받이가 배경에 적절히 배치되어 운전석 뒤쪽 공간임을 잘 보여줌.",
        "entities": "고무줄로 묶인 낡은 회수권 뭉치는 레퍼런스의 질감과 형태를 잘 살렸으며, 손목 부분에 남색 유니폼 소매와 흰색 셔츠 소매 끝이 묘사됨.",
        "hard_violations": [],
        "physics": "쫙 펴진 손바닥이 회수권 뭉치를 수평으로 안정감 있게 받치고 있음."
       },
       {
        "label": "A",
        "direction": "카메라는 쫙 펴진 손바닥과 그 위의 회수권 뭉치를 약간 위쪽에서 비스듬히 내려다보고 있음.",
        "built_space": "버스 내부의 복도와 나열된 빈 좌석들이 배경으로 깊게 보이며, 프롬프트에서 요구한 운전석 바로 뒤 공간의 좁은 느낌보다는 일반적인 버스 복도의 시점이 강함.",
        "entities": "회수권 뭉치와 고무줄은 레퍼런스와 일치하나, 손과 팔 부분에 프롬프트가 요구한 남색 승무원 유니폼 소매가 완전히 누락되어 맨팔이 노출됨.",
        "hard_violations": [],
        "physics": "손바닥이 공중에 떠 있는 상태로 회수권 뭉치를 평평하게 받치고 있음."
       }
      ],
      "all_candidates_fail": false
     },
     "normalized": {
      "winner": "B",
      "ranking": [
       "B",
       "A"
      ],
      "verdicts": [
       {
        "label": "B",
        "score": 9,
        "verdict_ko": "지시된 남색 승무원 유니폼 소매를 정확히 반영하였으며, 어두운 창문과 낡은 시트 배경을 통해 프롬프트가 요구한 위치와 분위기를 훌륭하게 구현했습니다."
       },
       {
        "label": "A",
        "score": 5,
        "verdict_ko": "회수권 뭉치의 묘사는 레퍼런스와 유사하나, 인물의 손목에 명시된 남색 유니폼 소매가 누락된 맨팔로 묘사되었고 배경이 지시된 위치의 느낌을 제대로 살리지 못했습니다."
       }
      ],
      "all_candidates_fail": false,
      "readings": [
       {
        "label": "B",
        "direction": "카메라는 쫙 펴진 손바닥 위에 놓인 회수권 뭉치를 수평에 가까운 앵글로 정면에서 클로즈업하여 바라보고 있음.",
        "built_space": "밤의 어두운 창문과 낡은 비닐 커버가 씌워진 버스 좌석 등받이가 배경에 적절히 배치되어 운전석 뒤쪽 공간임을 잘 보여줌.",
        "entities": "고무줄로 묶인 낡은 회수권 뭉치는 레퍼런스의 질감과 형태를 잘 살렸으며, 손목 부분에 남색 유니폼 소매와 흰색 셔츠 소매 끝이 묘사됨.",
        "hard_violations": [],
        "physics": "쫙 펴진 손바닥이 회수권 뭉치를 수평으로 안정감 있게 받치고 있음."
       },
       {
        "label": "A",
        "direction": "카메라는 쫙 펴진 손바닥과 그 위의 회수권 뭉치를 약간 위쪽에서 비스듬히 내려다보고 있음.",
        "built_space": "버스 내부의 복도와 나열된 빈 좌석들이 배경으로 깊게 보이며, 프롬프트에서 요구한 운전석 바로 뒤 공간의 좁은 느낌보다는 일반적인 버스 복도의 시점이 강함.",
        "entities": "회수권 뭉치와 고무줄은 레퍼런스와 일치하나, 손과 팔 부분에 프롬프트가 요구한 남색 승무원 유니폼 소매가 완전히 누락되어 맨팔이 노출됨.",
        "hard_violations": [],
        "physics": "손바닥이 공중에 떠 있는 상태로 회수권 뭉치를 평평하게 받치고 있음."
       }
      ]
     },
     "ok": true
    },
    {
     "model": "gpt",
     "order": "reverse",
     "display_to_canonical": {
      "A": "B",
      "B": "A"
     },
     "raw": {
      "winner": "A",
      "ranking": [
       "A",
       "B"
      ],
      "verdicts": [
       {
        "label": "A",
        "score": 6,
        "verdict_ko": "손바닥과 회수권 뭉치를 전경 중앙의 인서트 클로즈업으로 잡고 남색 제복 소매와 야간 버스 좌석 맥락도 보여 B보다 충실하지만, 회수권의 숫자가 읽혀 ‘읽을 수 있는 글자 금지’를 위반한다."
       },
       {
        "label": "B",
        "score": 4,
        "verdict_ko": "회수권의 형태와 물성은 정확하고 손의 지지도 자연스럽지만, 좌석과 통로를 과도하게 넓게 보여 인서트 구도가 약하며 정임의 남색 제복 소매가 보이지 않고 회수권 글자가 선명하게 읽힌다."
       }
      ],
      "readings": [
       {
        "label": "A",
        "direction": "시선이나 무기, 이동체는 없다. 손은 화면 오른쪽에서 왼쪽으로 뻗고 손바닥은 위를 향하며, 회수권 뭉치의 접힌 덮개와 종이 단면이 비스듬한 카메라 쪽 위로 향한다.",
        "built_space": "노후 버스 내부로 보이며 중앙 배경에 낡은 비닐 좌석 등받이 1개와 그 아래 같은 좌석의 방석 일부가 보이고, 뒤쪽 창문들은 완전한 밤의 어둠을 보인다. 손은 좌석 옆 전경에 떠 있어 지정된 위치와 대체로 양립하지만 좌석 가장자리가 배경에서 다소 크게 차지한다. 불가능한 반사는 없다.",
        "entities": "전경 중앙에 갈색 고무줄로 묶인 낡고 두꺼운 종이 회수권 뭉치 1개가 있으며 접힌 덮개와 겹친 종이 가장자리가 보인다. 젊은 한국인 여성 정임에게 어울리는 손과 손목, 남색 차장 제복 소매가 보이고 다른 인물은 없다. 얼굴과 모자는 프레임 밖이다. 회수권 표면의 숫자 일부는 읽을 수 있다.",
        "hard_violations": [
         "회수권 표면의 숫자와 인쇄 표기가 읽을 수 있는 상태로 노출되어 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
        ],
        "physics": "회수권 뭉치는 쫙 편 손바닥 위에 전체 밑면이 닿아 평평하게 지지되고 고무줄이 실제로 종이 뭉치를 조인다. 손과 손목은 오른쪽 프레임 밖의 팔로 이어지며 물체가 떠 있지 않는다."
       },
       {
        "label": "B",
        "direction": "시선이나 무기, 이동체는 없다. 손가락은 화면 오른쪽 위를 향하고 손바닥은 위를 향한다. 회수권의 인쇄면과 접힌 덮개, 층진 종이 가장자리는 비스듬한 카메라 쪽 위로 향한다.",
        "built_space": "노후 버스 내부이며 중앙을 거의 채우는 비닐 좌석 등받이 1개, 왼쪽 아래 방석, 손 아래의 좌석 모서리 또는 팔걸이, 오른쪽 배경의 여러 좌석과 고무 통로 매트가 보인다. 왼쪽 창밖은 밤이다. 손은 좌석 위에 기대어 있으나 넓은 통로와 다수 좌석이 보여 운전석 바로 뒤의 작은 좌석 가장자리만 남기는 지정 인서트보다 후방 객실처럼 읽힌다. 불가능한 반사는 없다.",
        "entities": "갈색 고무줄로 묶인 낡은 종이 회수권 뭉치 1개가 손바닥 위에 있고, 접힌 덮개와 마모된 종이층은 소품 참조와 매우 가깝다. 젊은 한국인 여성에게 가능한 손과 팔 일부만 보이며 다른 인물은 없다. 다만 남색 차장 제복 소매가 프레임 안에 전혀 나타나지 않아 정임의 복장 식별력이 약하다. 회수권의 숫자와 인쇄가 선명하게 읽힌다.",
        "hard_violations": [
         "회수권 표면의 숫자와 인쇄 표기가 선명하게 읽혀 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
        ],
        "physics": "회수권은 펼친 손바닥과 손가락에 닿아 지지되며 고무줄이 뭉치를 물리적으로 묶는다. 손목과 아래팔은 좌석 모서리에 기대어 추가로 지지되므로 떠 있는 물체나 신체 부위는 없다."
       }
      ],
      "all_candidates_fail": true
     },
     "normalized": {
      "winner": "B",
      "ranking": [
       "B",
       "A"
      ],
      "verdicts": [
       {
        "label": "B",
        "score": 6,
        "verdict_ko": "손바닥과 회수권 뭉치를 전경 중앙의 인서트 클로즈업으로 잡고 남색 제복 소매와 야간 버스 좌석 맥락도 보여 B보다 충실하지만, 회수권의 숫자가 읽혀 ‘읽을 수 있는 글자 금지’를 위반한다."
       },
       {
        "label": "A",
        "score": 4,
        "verdict_ko": "회수권의 형태와 물성은 정확하고 손의 지지도 자연스럽지만, 좌석과 통로를 과도하게 넓게 보여 인서트 구도가 약하며 정임의 남색 제복 소매가 보이지 않고 회수권 글자가 선명하게 읽힌다."
       }
      ],
      "all_candidates_fail": true,
      "readings": [
       {
        "label": "B",
        "direction": "시선이나 무기, 이동체는 없다. 손은 화면 오른쪽에서 왼쪽으로 뻗고 손바닥은 위를 향하며, 회수권 뭉치의 접힌 덮개와 종이 단면이 비스듬한 카메라 쪽 위로 향한다.",
        "built_space": "노후 버스 내부로 보이며 중앙 배경에 낡은 비닐 좌석 등받이 1개와 그 아래 같은 좌석의 방석 일부가 보이고, 뒤쪽 창문들은 완전한 밤의 어둠을 보인다. 손은 좌석 옆 전경에 떠 있어 지정된 위치와 대체로 양립하지만 좌석 가장자리가 배경에서 다소 크게 차지한다. 불가능한 반사는 없다.",
        "entities": "전경 중앙에 갈색 고무줄로 묶인 낡고 두꺼운 종이 회수권 뭉치 1개가 있으며 접힌 덮개와 겹친 종이 가장자리가 보인다. 젊은 한국인 여성 정임에게 어울리는 손과 손목, 남색 차장 제복 소매가 보이고 다른 인물은 없다. 얼굴과 모자는 프레임 밖이다. 회수권 표면의 숫자 일부는 읽을 수 있다.",
        "hard_violations": [
         "회수권 표면의 숫자와 인쇄 표기가 읽을 수 있는 상태로 노출되어 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
        ],
        "physics": "회수권 뭉치는 쫙 편 손바닥 위에 전체 밑면이 닿아 평평하게 지지되고 고무줄이 실제로 종이 뭉치를 조인다. 손과 손목은 오른쪽 프레임 밖의 팔로 이어지며 물체가 떠 있지 않는다."
       },
       {
        "label": "A",
        "direction": "시선이나 무기, 이동체는 없다. 손가락은 화면 오른쪽 위를 향하고 손바닥은 위를 향한다. 회수권의 인쇄면과 접힌 덮개, 층진 종이 가장자리는 비스듬한 카메라 쪽 위로 향한다.",
        "built_space": "노후 버스 내부이며 중앙을 거의 채우는 비닐 좌석 등받이 1개, 왼쪽 아래 방석, 손 아래의 좌석 모서리 또는 팔걸이, 오른쪽 배경의 여러 좌석과 고무 통로 매트가 보인다. 왼쪽 창밖은 밤이다. 손은 좌석 위에 기대어 있으나 넓은 통로와 다수 좌석이 보여 운전석 바로 뒤의 작은 좌석 가장자리만 남기는 지정 인서트보다 후방 객실처럼 읽힌다. 불가능한 반사는 없다.",
        "entities": "갈색 고무줄로 묶인 낡은 종이 회수권 뭉치 1개가 손바닥 위에 있고, 접힌 덮개와 마모된 종이층은 소품 참조와 매우 가깝다. 젊은 한국인 여성에게 가능한 손과 팔 일부만 보이며 다른 인물은 없다. 다만 남색 차장 제복 소매가 프레임 안에 전혀 나타나지 않아 정임의 복장 식별력이 약하다. 회수권의 숫자와 인쇄가 선명하게 읽힌다.",
        "hard_violations": [
         "회수권 표면의 숫자와 인쇄 표기가 선명하게 읽혀 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
        ],
        "physics": "회수권은 펼친 손바닥과 손가락에 닿아 지지되며 고무줄이 뭉치를 물리적으로 묶는다. 손목과 아래팔은 좌석 모서리에 기대어 추가로 지지되므로 떠 있는 물체나 신체 부위는 없다."
       }
      ]
     },
     "ok": true
    }
   ],
   "models": [
    "gemini-pro",
    "gpt"
   ],
   "slot_winner_match": true,
   "slot_winner": {
    "gemini-pro": "B",
    "gpt": "B"
   },
   "route": "cross_slot_agree"
  },
  "dual": {
   "models": [
    "gemini-pro",
    "gpt"
   ],
   "normalized": {
    "A": 1.222,
    "B": 2.0
   },
   "adjusted": {
    "A": 0.972,
    "B": 1.75
   },
   "violations": {
    "B": [
     "[gpt] 회수권 표면의 숫자와 인쇄 표기가 읽을 수 있는 상태로 노출되어 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
    ],
    "A": [
     "[gpt] 회수권 표면의 숫자와 인쇄 표기가 선명하게 읽혀 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
    ]
   },
   "per_model_winner": {
    "gemini-pro": "B",
    "gpt": "B"
   },
   "agreed": true
  },
  "totals": {
   "B": 1750,
   "A": 972
  },
  "selected": "B",
  "ranking": [
   "B",
   "A"
  ],
  "verdicts": [
   {
    "label": "B",
    "score": 1750,
    "verdict_ko": "지시된 남색 승무원 유니폼 소매를 정확히 반영하였으며, 어두운 창문과 낡은 시트 배경을 통해 프롬프트가 요구한 위치와 분위기를 훌륭하게 구현했습니다.  ★위반: [gpt] 회수권 표면의 숫자와 인쇄 표기가 읽을 수 있는 상태로 노출되어 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
   },
   {
    "label": "A",
    "score": 972,
    "verdict_ko": "회수권 뭉치의 묘사는 레퍼런스와 유사하나, 인물의 손목에 명시된 남색 유니폼 소매가 누락된 맨팔로 묘사되었고 배경이 지시된 위치의 느낌을 제대로 살리지 못했습니다.  ★위반: [gpt] 회수권 표면의 숫자와 인쇄 표기가 선명하게 읽혀 ‘읽을 수 있는 글자 없음’ 조건을 위반한다."
   }
  ],
  "refs": [
   {
    "label": "LOCATION PHOTOGRAPH — the exact place of this shot: its architecture, materials, fixed features and lighting mood are spatial truth; stage the moment inside this place. Never copy its camera framing.",
    "path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.png",
    "asset_id": "9e975568-11df-4493-a43b-8bda7e806e30",
    "role": "location_plate"
   },
   {
    "label": "CHARACTER REFERENCE — 정임: the exact person appearing in this shot; match face, hair and build exactly.",
    "path": "<bytes:1254053>",
    "asset_id": "db331b24-c065-4549-a6ef-681b9e52c8fa",
    "role": "character_ref"
   },
   {
    "label": "PROP REFERENCE — 고무줄로 묶인 낡은 종이 회수권 뭉치: the exact object appearing in this shot; match its look, material and wear exactly.",
    "path": "<bytes:1135067>",
    "asset_id": "6e82ce93-8876-47c1-ac1d-48cf6c9a06d7",
    "role": "prop_ref"
   }
  ],
  "critique_skipped": true,
  "shot_run_produced": true,
  "shot_run_uid": "06a928e5-86af-7577-a7f0-24001d5cfb95",
  "bgfirst": {
   "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/scene/recipe/S3sh5__bgfirst_bg.png",
   "bg_asset_id": "bd974e7a-805b-4177-b546-9163b0ef8099",
   "bg_record_key": "S3sh5::bgfirst_bg",
   "chain_winner": false,
   "authority": "plate"
  },
  "ref_mode": "플레이트+엔티티 (2택1: 무콘티 승)",
  "share_plan": {
   "ref_plan": "background"
  }
 },
 "S3sh5::cine": {
  "applied": true,
  "attempted_at": "2026-08-29T07:49:54.253172+00:00",
  "fingerprint": "3b3e469215b6a391c3713bd979c67c919ff460757739c75cd9d1f865f7bcd853",
  "fingerprint_version": 2,
  "provider": "reve",
  "endpoint": "reve/2.1/edit",
  "model": "reve/2.1/edit",
  "pack": "24.202608252115",
  "source_file": "S3sh5_sel.png",
  "source_sha256": "79653a1fd2e0706e006ebd87f08dbec28f07ff576aadc38770a4480607882a91",
  "file": "S3sh5_cine.png",
  "staged_sha256": "a68e235a87ad5c41f40b2eae4fdff0417baf550ea52a1451ed1a26b8c2566fcc",
  "latency_ms": 59541,
  "request_id": "01a04c7f-2b12-7de1-9400-2d890a8f48d9",
  "status_url": "https://queue.fal.run/reve/2.1/requests/01a04c7f-2b12-7de1-9400-2d890a8f48d9/status",
  "response_url": "https://queue.fal.run/reve/2.1/requests/01a04c7f-2b12-7de1-9400-2d890a8f48d9",
  "submitted_at": "2026-08-29T07:49:57.699465+00:00"
 },
 "S3sh9::confined_fp_apt": {
  "applies": true,
  "reason_ko": "버스 내부의 앞부분으로 운전석, 요금함, 출입문 등 특정한 구조물과 인물(안내양과 탑승객)의 위치 관계가 명확하게 유지되어야 하는 차량 실내 씬이므로 평면도 레이아웃 보조가 필요합니다.",
  "input_fingerprint": "838a9874aa6e3d7e"
 }
}