Ingeniería y CAD / Tarea de muestra
Muestra pública generada
Modelar un soporte a partir de su plano.
Una tarea completa de plano a modelo. Todos los archivos se generan a partir de un único conjunto de parámetros; no es una pieza real de ninguna empresa.
- Ámbito
- Piezas mecánicas
- Familia de tareas
- Del plano al modelo sólido
- Modo de acceso
- Archivos, kernel CAD sin interfaz gráfica
- Entregable
- Un sólido STEP
- Verificador
- Geometría determinista: 3 filtros, 10 comprobaciones
- Límite de tiempo
- 45 minutos
- Partición
- Muestra pública, nunca en un conjunto de entrenamiento ni de evaluación
Plano de referencia
DUF-S-001, rev. A.
Tres vistas en proyección del tercer diedro, generadas a partir de los mismos parámetros que el modelo patrón, de modo que el plano y la respuesta no pueden divergir. El ámbar marca el agujero con tolerancia que mide el verificador.
Véala en ejecución
Compare los envíos.
Resultados registrados del verificador. El amarillo marca las comprobaciones fallidas; despliegue un informe para ver cada medición.
Enviado
output/bracket.step ← tests/gold/bracket.step 91,297 bytes · sha256 1785336204458725… The gold solid the verifier compares against gold solid: must pass strict · as expected, 0.87 s
output/bracket.step ← written by solution/solve.py (85,015 bytes, built in 0.61 s) solution/solve.py: 7,551 bytes · sha256 ae73b38a9cc37870… The reference solution: solution/solve.py builds the part from the drawing’s dimensions with OCP reference solution: must pass strict · as expected, 0.91 s
output/bracket.step ← tests/probes/alt_rebuilt.step 83,731 bytes · sha256 9a4dc6d362af2d15… Built another way: two outlines fused, one revolved bore cutter, fillet last; STEP AP242 correct alternative: must pass strict · as expected, 0.88 s
output/bracket.step ← tests/probes/alt_bore_18009.step 91,386 bytes · sha256 00e293e59fc76bb1… The bore at Ø18.009, inside H7, everything else gold correct alternative: must pass strict · as expected, 0.82 s
output/bracket.step ← tests/probes/alt_split_faces.step 118,131 bytes · sha256 69c196eb32cbaa4a… The gold with every closed face split in two, as some CAD systems write it correct alternative: must pass strict · as expected, 0.87 s
output/bracket.step ← tests/probes/empty.step 0 bytes · sha256 e3b0c44298fc1c14… An empty bracket.step reward hack: must score exactly 0 · as expected, 0.68 s
output/bracket.step ← a note, and no output/bracket.step 61 bytes · sha256 a1fbda2711798837… No model, only a note saying the part was modelled and checked reward hack: must score exactly 0 · as expected, 0.68 s
output/bracket.step ← tests/probes/scaled_copy.step 96,498 bytes · sha256 7a19df708266b18d… The gold solid scaled by 1.02 plausible mistake: must fail strict, caught by C1 to C8 · as expected, 0.91 s
output/bracket.step ← tests/probes/bore_oversize.step 91,317 bytes · sha256 201c90aa78c85c88… The bore 0.4 mm oversize, everything else gold plausible mistake: must fail strict, caught by C4 · as expected, 0.82 s
output/bracket.step ← tests/probes/three_holes.step 86,917 bytes · sha256 d8f2fa15affd4f7e… One base hole left out plausible mistake: must fail strict, caught by C6, C7 · as expected, 0.88 s
output/bracket.step ← tests/probes/mirrored.step 89,522 bytes · sha256 28dcdc826bc8b551… The gold solid mirrored left to right plausible mistake: must fail strict, caught by C3, C8, C10 · as expected, 0.91 s
output/bracket.step ← tests/probes/spline_faces.step 135,874 bytes · sha256 5a1a0ede8035bf36… The gold with every face converted to a B-spline surface: same shape, no true cylinders plausible mistake: must fail strict, caught by C9 · as expected, 1.87 s
Salida del verificador · gold estricto: pasa · recompensa 1 · puntuación 1.00
Todos los filtros y comprobaciones superados.
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 91297 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 25 faces, volume 209268.6 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 1.0000 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 13 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass true reward 1 score 1.00
Salida del verificador · solve_py estricto: pasa · recompensa 1 · puntuación 1.00
Todos los filtros y comprobaciones superados.
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 85015 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 24 faces, volume 209265.5 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 1.0000 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0090, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 12 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass true reward 1 score 1.00
Salida del verificador · alt_rebuilt estricto: pasa · recompensa 1 · puntuación 1.00
Todos los filtros y comprobaciones superados.
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 83731 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 24 faces, volume 209268.6 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 1.0000 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 12 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass true reward 1 score 1.00
Salida del verificador · alt_bore_18009 estricto: pasa · recompensa 1 · puntuación 1.00
Todos los filtros y comprobaciones superados.
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 91386 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 25 faces, volume 209265.5 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 1.0000 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0090, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 13 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass true reward 1 score 1.00
Salida del verificador · alt_split_faces estricto: pasa · recompensa 1 · puntuación 1.00
Todos los filtros y comprobaciones superados.
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 118131 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 32 faces, volume 209268.6 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 1.0000 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 4 cone, 18 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass true reward 1 score 1.00
Salida del verificador · empty estricto: falla · recompensa 0 · puntuación 0.00
G1 FAIL output/bracket.step exists, is not empty and reads as STEP: the file is empty (0 bytes)
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 FAIL output/bracket.step exists, is not empty and reads as STEP: the file is empty (0 bytes) checks not scored: a gate failed strict_pass false reward 0 score 0.00
Salida del verificador · claim_only estricto: falla · recompensa 0 · puntuación 0.00
G1 FAIL output/bracket.step exists, is not empty and reads as STEP: no file at output/bracket.step
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 FAIL output/bracket.step exists, is not empty and reads as STEP: no file at output/bracket.step checks not scored: a gate failed strict_pass false reward 0 score 0.00
Salida del verificador · scaled_copy estricto: falla · recompensa 0 · puntuación 0.10
C1 FAIL Envelope: 122.400 × 81.600 × 85.680 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 FAIL Volume: 222.08 cm³ (+6.12%) expected 209.27 cm³ ±0.5% · w10 C3 FAIL Overlap with the gold (IoU): 0.8386 expected ≥ 0.995 · w10 C4 FAIL Bore diameter: Ø18.3600, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 FAIL Bore axis: position, square to B: X 61.200, Z 53.040; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 FAIL Through holes: count and diameter: 4 through, all Ø9.180 expected 4 × Ø9.0 ±0.10, through · w10 C7 FAIL Hole pattern: centre positions: 0 of 4 within 0.10, worst 2.100 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 FAIL Slot: width, length, centre: 10.200 × 30.600 at (42.840, 30.600) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 96498 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 25 faces, volume 222077.5 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 122.40 × 81.60 × 85.68 mm C1 FAIL Envelope: 122.400 × 81.600 × 85.680 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 FAIL Volume: 222.08 cm³ (+6.12%) expected 209.27 cm³ ±0.5% · w10 C3 FAIL Overlap with the gold (IoU): 0.8386 expected ≥ 0.995 · w10 C4 FAIL Bore diameter: Ø18.3600, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 FAIL Bore axis: position, square to B: X 61.200, Z 53.040; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 FAIL Through holes: count and diameter: 4 through, all Ø9.180 expected 4 × Ø9.0 ±0.10, through · w10 C7 FAIL Hole pattern: centre positions: 0 of 4 within 0.10, worst 2.100 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 FAIL Slot: width, length, centre: 10.200 × 30.600 at (42.840, 30.600) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 13 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.84 < bore X 61.20: left expected slot left of the bore, seen from the front · w5 strict_pass false reward 0 score 0.10
Salida del verificador · bore_oversize estricto: falla · recompensa 0 · puntuación 0.80
C4 FAIL Bore diameter: Ø18.4000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 91317 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 25 faces, volume 209130.1 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.13 cm³ (-0.07%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 0.9993 expected ≥ 0.995 · w10 C4 FAIL Bore diameter: Ø18.4000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 13 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass false reward 0 score 0.80
Salida del verificador · three_holes estricto: falla · recompensa 0 · puntuación 0.80
C6 FAIL Through holes: count and diameter: 3 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 FAIL Hole pattern: centre positions: 3 of 4 within 0.10, worst 0.000, 1 missing expected 90.0 × 36.0 from (15, 14), ±0.10 · w10
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 86917 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 24 faces, volume 210032.0 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 210.03 cm³ (+0.36%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 0.9964 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 FAIL Through holes: count and diameter: 3 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 FAIL Hole pattern: centre positions: 3 of 4 within 0.10, worst 0.000, 1 missing expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 12 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass false reward 0 score 0.80
Salida del verificador · mirrored estricto: falla · recompensa 0 · puntuación 0.75
C3 FAIL Overlap with the gold (IoU): 0.9686 expected ≥ 0.995 · w10 C8 FAIL Slot: width, length, centre: 10.000 × 30.000 at (78.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C10 FAIL Handedness: slot X 78.00 > bore X 60.00: right expected slot left of the bore, seen from the front · w5
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 89522 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 25 faces, volume 209268.6 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 FAIL Overlap with the gold (IoU): 0.9686 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 FAIL Slot: width, length, centre: 10.000 × 30.000 at (78.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 ok Feature types: all present · faces: 2 cone, 13 cylinder, 10 plane expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 FAIL Handedness: slot X 78.00 > bore X 60.00: right expected slot left of the bore, seen from the front · w5 strict_pass false reward 0 score 0.75
Salida del verificador · spline_faces estricto: falla · recompensa 0 · puntuación 0.95
C9 FAIL Feature types: missing: bore cylinder; 0/4 hole cylinders; R6 fillet ×0; R10 rounds ×0; 1×45° chamfers ×0 · faces: 25 B-spline expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5
Salida completa del verificador
$ bash tests/test.sh output/bracket.step G1 ok output/bracket.step exists, is not empty and reads as STEP: 135874 bytes, read as STEP G2 ok exactly one closed, valid solid with positive volume: 1 closed valid solid, 25 faces, volume 209268.6 mm³ G3 ok units are millimetres and the part fits inside a 250 mm cube: millimetre; extent 120.00 × 80.00 × 84.00 mm C1 ok Envelope: 120.000 × 80.000 × 84.000 expected 120.0 × 80.0 × 84.0 ±0.10 · w10 C2 ok Volume: 209.27 cm³ (+0.00%) expected 209.27 cm³ ±0.5% · w10 C3 ok Overlap with the gold (IoU): 1.0000 expected ≥ 0.995 · w10 C4 ok Bore diameter: Ø18.0000, 3 sections within 0.0000 expected Ø18 H7: 18.000 to 18.018 · w20 C5 ok Bore axis: position, square to B: X 60.000, Z 52.000; square 0.0000 expected X 60.00, Z 52.00 ±0.05; square ≤ 0.02 · w10 C6 ok Through holes: count and diameter: 4 through, all Ø9.000 expected 4 × Ø9.0 ±0.10, through · w10 C7 ok Hole pattern: centre positions: 4 of 4 within 0.10, worst 0.000 expected 90.0 × 36.0 from (15, 14), ±0.10 · w10 C8 ok Slot: width, length, centre: 10.000 × 30.000 at (42.000, 30.000) expected 10.0 × 30.0 at (42, 30) ±0.10 · w10 C9 FAIL Feature types: missing: bore cylinder; 0/4 hole cylinders; R6 fillet ×0; R10 rounds ×0; 1×45° chamfers ×0 · faces: 25 B-spline expected bore and holes true cylinders; R6 fillet, 4 × R10, 2 × 1×45° chamfers · w5 C10 ok Handedness: slot X 42.00 < bore X 60.00: left expected slot left of the bore, seen from the front · w5 strict_pass false reward 0 score 0.95
Enunciado de la tarea
Lo que se le dice al agente.
La instrucción que recibe el agente, junto con los archivos y las herramientas a los que puede acceder.
instruction.md818 bytes
# Model the bracket on drawing DUF-S-001 `project/drawing.svg` is a released drawing (rev A) of a mounting bracket. Model it as one solid and export it as STEP (AP214 or AP242) to `output/bracket.step`. - Work in millimetres. Put the origin where datums A, B and C meet, with +X along the front edge, +Y towards the web and +Z up. - Model every feature on the drawing: the four through holes, the slot, the bore with its chamfers, the rounds and the inner fillet. - Model the Ø18 H7 bore at a diameter inside its tolerance (18.000 to 18.018). - The drawing governs. Where it is silent, ISO 2768-m applies. - Python 3.12 with OpenCascade (OCP, the kernel CadQuery is built on) and numpy is installed. You have no network access. When the file is written, say so in one line. Do not describe checks you did not run.
- El agente ve
project/drawing.svgy una carpetaoutput/vacía, en/workspace- Herramientas
- Una shell, Python 3.12 con OpenCascade (OCP) y numpy, tal como los instala el Dockerfile; sin red
- Oculto para él
- El sólido patrón, las pruebas y las comprobaciones en
tests/, que se copian solo cuando termina la ejecución, y la solución de referencia ensolution/ - Variantes
- El generador toma como parámetros todas las cotas, el patrón de orificios y el ajuste, de modo que una sola familia produce muchas tareas distintas
Entregable y verificador
Calificado por la geometría, elemento a elemento.
Primero los filtros: una respuesta ausente, dañada o en unidades equivocadas obtiene 0. Después, diez comprobaciones ponderadas, cada una una medición con una tolerancia indicada. Primero se comparan las formas globales. Después se mide por separado cada elemento con tolerancia, en secciones cortadas a través del sólido enviado, y se comprueba el tipo de sus caras.
- Archivo
output/bracket.step, STEP AP214 o AP242, exactamente un sólido- Sistema de referencia
- Milímetros, origen en las referencias A, B y C, Z hacia arriba; el verificador también alinea las caras de referencia antes de comparar
- No se califica
- Árbol de operaciones, nombres de cuerpos, colores, capas, cómo se construyó el modelo
- Recompensa
- 1 solo si pasan todos los filtros y cada una de las diez comprobaciones (aprobado estricto); en caso contrario, 0. Es la recompensa de entrenamiento
- Puntuación
- Suma de los pesos de las comprobaciones superadas, dividida entre 100; 0 si falla cualquier filtro. Muestra dónde falló una respuesta
Filtros
| Filtro | Debe cumplirse |
|---|---|
| G1 | output/bracket.step existe, no está vacío y se lee como STEP |
| G2 | Contiene exactamente un sólido cerrado y válido con volumen positivo |
| G3 | Las unidades son milímetros y la pieza cabe dentro de un cubo de 250 mm |
Comprobaciones
| Comprobación | Qué se mide | Objetivo | Tolerancia | Peso |
|---|---|---|---|---|
| C1 | Envolvente | 120.0 × 80.0 × 84.0 mm | ±0.10 mm | 10 |
| C2 | Volumen | 209.27 cm³ (patrón) | ±0.5% | 10 |
| C3 | Solapamiento con el sólido patrón, alineado en A, B, C | Intersección sobre unión | al menos 0.995 | 10 |
| C4 | Diámetro del agujero, un círculo ajustado a la pared del agujero en tres secciones | Ø18 H7 | de 18.000 a 18.018 mm | 20 |
| C5 | Eje del agujero: posición y perpendicularidad respecto a B | X 60.00, Z 52.00 | ±0.05 mm; 0.02 mm | 10 |
| C6 | Orificios pasantes en la base: número y diámetro | 4 × Ø9.0, pasantes | ±0.10 mm | 10 |
| C7 | Patrón de orificios: posiciones de los centros | 90.0 × 36.0, primer orificio en (15, 14) | ±0.10 mm | 10 |
| C8 | Ranura: anchura, longitud, centro | 10.0 × 30.0, centro (42, 30) | ±0.10 mm | 10 |
| C9 | Tipos de elementos presentes | Agujero y orificios como cilindros verdaderos; redondeo interior R6, cuatro redondeos R10, dos chaflanes de 1 × 45° en el agujero | por tipo de cara; radios según ISO 2768-m | 5 |
| C10 | Lateralidad | Ranura a la izquierda del agujero, vista de frente | exacta | 5 |
C4, en ámbar en el plano y en el modelo, es la comprobación que una comparación de forma global no puede sustituir.
Pruebas
Respuestas erróneas que debe rechazar, correctas que debe aprobar.
Antes de entregar una tarea, su verificador se ejecuta sobre la salida de la solución de referencia, sobre respuestas erróneas a propósito y sobre alternativas correctas construidas de otra forma. Los reward hacks deben obtener exactamente 0, cada error plausible debe fallar en modo estricto en las comprobaciones que se diseñó para hacer saltar, y la solución de referencia y cada alternativa correcta deben pasar. Cada fila de abajo procede de la ejecución registrada.
Todos los envíos de prueba y sus mediciones
| Envío | Qué es | Tipo | Medido por el verificador | Detectado por | Puntuación | Estricta |
|---|---|---|---|---|---|---|
gold | El sólido patrón con el que compara el verificador | sólido patrón | envolvente dentro de 0.10; volumen +0.00%; solapamiento 1.0000; agujero Ø18.0000 | Nada | 1.00 | Pasa |
solve_py | La solución de referencia: solution/solve.py construye la pieza a partir de las cotas del plano con OCP | solución de referencia | envolvente dentro de 0.10; volumen +0.00%; solapamiento 1.0000; agujero Ø18.0090 | Nada | 1.00 | Pasa |
alt_rebuilt | Construido de otra forma: dos contornos fusionados, un cortador de revolución para el agujero, redondeo al final; STEP AP242 | alternativa correcta | envolvente dentro de 0.10; volumen +0.00%; solapamiento 1.0000; agujero Ø18.0000 | Nada | 1.00 | Pasa |
alt_bore_18009 | El agujero a Ø18,009, dentro de H7, todo lo demás igual que el patrón | alternativa correcta | envolvente dentro de 0.10; volumen +0.00%; solapamiento 1.0000; agujero Ø18.0090 | Nada | 1.00 | Pasa |
alt_split_faces | El patrón con cada cara cerrada dividida en dos, como lo escriben algunos sistemas CAD | alternativa correcta | envolvente dentro de 0.10; volumen +0.00%; solapamiento 1.0000; agujero Ø18.0000 | Nada | 1.00 | Pasa |
empty | Un bracket.step vacío | reward hack | El archivo está vacío (0 bytes) | G1 | 0.00 | Falla |
claim_only | Sin modelo, solo una nota que dice que la pieza se modeló y se comprobó | reward hack | No hay archivo en output/bracket.step | G1 | 0.00 | Falla |
scaled_copy | El sólido patrón escalado por 1,02 | error plausible | envolvente 122.400 × 81.600 × 85.680; volumen +6.12%; solapamiento 0.8386; agujero Ø18.3600 | De C1 a C8 | 0.10 | Falla |
bore_oversize | El agujero 0,4 mm sobredimensionado, todo lo demás igual que el patrón | error plausible | envolvente dentro de 0.10; volumen -0.07%; solapamiento 0.9993; agujero Ø18.4000 | C4 | 0.80 | Falla |
three_holes | Un orificio de la base omitido | error plausible | envolvente dentro de 0.10; volumen +0.36%; solapamiento 0.9964; agujero Ø18.0000; orificios pasantes: 3 pasantes, todos Ø9.000; patrón de orificios: 3 de 4 dentro de 0.10, peor 0.000, 1 ausente | C6, C7 | 0.80 | Falla |
mirrored | El sólido patrón reflejado de izquierda a derecha | error plausible | envolvente dentro de 0.10; volumen +0.00%; solapamiento 0.9686; agujero Ø18.0000; ranura 10.000 × 30.000 en (78.000, 30.000); lateralidad: ranura X 78.00 > agujero X 60.00: derecha | C3, C8, C10 | 0.75 | Falla |
spline_faces | El patrón con cada cara convertida en una superficie B-spline: misma forma, ningún cilindro verdadero | error plausible | envolvente dentro de 0.10; volumen +0.00%; solapamiento 1.0000; agujero Ø18.0000; ningún cilindro, cono ni plano verdadero | C9 | 0.95 | Falla |
Generado a partir de tests/run_results.json, la ejecución de la sección siguiente. El agujero sobredimensionado pasa la envolvente, el volumen y el solapamiento, y solo se detecta cuando se mide el agujero, como en nuestro propio estudio de geometría. La copia B-spline tiene la forma correcta y solo falla en el tipo de elemento: un sistema CAM o un inspector no encuentra en ella ningún cilindro verdadero que tomar como agujero.
tests/verify.py · cómo miden el agujero C4 y C5def measure_bore(solid):
"""The Ø18 H7 bore. Cut the web square to the bore at three depths, clear of the
1 mm chamfers; fit a circle to the bore's outline in each section. The diameter is
each circle's; the axis runs through the centres (position and squareness, C5)."""
y0, y1 = web_faces(solid) # the web's front and back faces, measured
ch = SPEC["bore"]["chamfer"]
depths = (y0 + ch + 0.5, (y0 + y1) / 2, y1 - ch - 0.5)
nominal = np.array([SPEC["bore"]["x"], SPEC["bore"]["z"]])
rings = []
for y in depths:
loops = round_loops(section_loops(solid, "y", y)) # inner loops that are circles
near = [l for l in loops if np.linalg.norm(l["centre"] - nominal) < 15]
if not near:
return None # no bore: C4 and C5 fail
rings.append(min(near, key=lambda l: np.linalg.norm(l["centre"] - nominal)))
shift = np.linalg.norm(rings[2]["centre"] - rings[0]["centre"])
tilt = shift * (y1 - y0) / (depths[2] - depths[0]) # over the web's thickness
return dict(d=[l["d"] for l in rings], centre=rings[1]["centre"], square=float(tilt),
roundness=max(l["roundness"] for l in rings))
Medido en la pieza, no leído del archivo
El verificador nunca se fía de la etiqueta propia de un elemento. Corta el sólido perpendicularmente al agujero a tres profundidades alejadas de los chaflanes y ajusta un círculo al contorno del agujero en cada una. El diámetro debe quedar dentro de la banda H7 de 18 µm en todas las secciones; el eje que pasa por los centros da la posición y la perpendicularidad.
Los orificios y la ranura se miden de la misma manera, en secciones a través de la base cerca de ambas caras y a media altura del espesor, de modo que un orificio solo cuenta si es pasante. Los tipos de elementos (C9) son la única comprobación que se lee de las definiciones propias de las caras.
Carpeta de la tarea
Qué se entrega, archivo por archivo.
La descarga contiene cada uno de los archivos que se enumeran abajo, incluida la ejecución registrada y los scripts necesarios para reproducirla.
| Ruta | Qué es | Tamaño |
|---|---|---|
task.toml | Id, ámbito, modo de acceso, límite de tiempo, partición, contenedor, comando del verificador, regla de recompensa, comando de la solución, derechos | 1.1 KB |
instruction.md | El enunciado anterior | 818 B |
environment/Dockerfile | El contenedor del agente: Python 3.12, OpenCascade mediante OCP, numpy, el plano; no se descarga nada en tiempo de ejecución | 1.0 KB |
environment/project/drawing.svg | El plano de referencia, rev. A | 21.6 KB |
tests/test.sh | Ejecuta el verificador; escribe primero una recompensa de 0, de modo que un bloqueo o un tiempo agotado sigan puntuando 0 | 836 B |
tests/verify.py | Los filtros y las diez comprobaciones | 27.0 KB |
tests/gold/bracket.step | El sólido patrón, del lado del evaluador | 91.3 KB |
tests/probes/ | Las pruebas: 8 sólidos STEP, un archivo vacío, una nota de solo afirmación y probes.json, que indica qué debe obtener cada envío | 796.1 KB |
tests/run_probes.py | Ejecuta la solución de referencia, después el verificador sobre su salida, el sólido patrón y cada prueba, y comprueba cada resultado | 5.1 KB |
tests/run_results.json | La ejecución que se muestra en esta página | 36.9 KB |
solution/solve.sh | Ejecuta solve.py y escribe output/bracket.step | 398 B |
solution/solve.py | La solución de referencia: construye el soporte a partir de las cotas del plano con OCP, sin leer el sólido patrón | 7.6 KB |
Descargar la carpeta de la tarea ZIP, 177,3 KB · una muestra pública generada, no un elemento de evaluación
La ejecución anterior se realizó en el contenedor que construye el Dockerfile, sin red: primero se ejecutó la solución de referencia sin tests/ y después se añadió y ejecutó el verificador.
¿Quiere tareas como esta para su harness?
Indíquenos la capacidad que está entrenando y el formato que admite su harness. Vea los datos de ingeniería y CAD con los que construimos tareas, y cómo construimos entornos.