kyeongmin
c59864eb9a
Some checks failed
Multi-MDX Regression (IMP-91) / multi-mdx-regression (push) Failing after 31s
- u2~u5: tests/integration/test_multi_mdx_regression.py — MDX_SET=(01..05) cached integration runs + status/structural/visual snapshots + full_mdx_coverage assertion (9 snapshots populated for 01-05). - u6~u11: F0 normalize / F1 V4 ranking / F2 slot_payload / F3 classifier-only AI / F4 layout / F5 final.html axis per MDX_SET. - u12: pyproject.toml — pytest-json-report>=1.5 in dev extras. - u13: .github/workflows/multi-mdx-regression.yml — pytest+artifact CI. - u14: scripts/update_status_board.py + tests/scripts/test_update_status_board.py — idempotent JSON marker updater (3 unit tests pass). - u15: PHASE-Z-PIPELINE-STATUS-BOARD.md — 30 F0-F5 × mdx01-05 markers initialized `?` + workflow wiring. Stage 4 verify: 59/59 PASS targeted (smoke 6 + updater 3 + integration 50), 386/386 PASS regression umbrella, 0 failures. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
113 lines
3.6 KiB
JSON
113 lines
3.6 KiB
JSON
{
|
|
"_doc": "IMP-91 u7 — F1 V4 ranking observed snapshot (step05_v4_evidence). Pins v4_source (POSIX-normalized), aligned_section_ids, and per-section {section_id, candidate_status, candidates: [{template_id, label, confidence}]}. confidence kept at current 4-decimal rounding. Sections appear in pipeline-emitted order.",
|
|
"01": {
|
|
"v4_source": "tests/matching/v4_full32_result.yaml",
|
|
"aligned_section_ids": ["01-1", "01-2"],
|
|
"sections": [
|
|
{
|
|
"section_id": "01-1",
|
|
"candidate_status": "ok",
|
|
"candidates": [
|
|
{"template_id": "construction_bim_three_usage", "label": "use_as_is", "confidence": 0.9101},
|
|
{"template_id": "construction_goals_three_circle_intersection", "label": "light_edit", "confidence": 0.8261},
|
|
{"template_id": "dx_sw_necessity_three_perspectives", "label": "light_edit", "confidence": 0.8168}
|
|
]
|
|
},
|
|
{
|
|
"section_id": "01-2",
|
|
"candidate_status": "ok",
|
|
"candidates": [
|
|
{"template_id": "bim_dx_comparison_table", "label": "use_as_is", "confidence": 0.9459},
|
|
{"template_id": "app_sw_package_vs_solution", "label": "restructure", "confidence": 0.6813}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"02": {
|
|
"v4_source": "tests/matching/v4_full32_result.yaml",
|
|
"aligned_section_ids": ["02-1", "02-2-sub-1", "02-2-sub-2"],
|
|
"sections": [
|
|
{
|
|
"section_id": "02-1",
|
|
"candidate_status": "ok",
|
|
"candidates": [
|
|
{"template_id": "construction_goals_three_circle_intersection", "label": "use_as_is", "confidence": 0.914}
|
|
]
|
|
},
|
|
{
|
|
"section_id": "02-2-sub-1",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
},
|
|
{
|
|
"section_id": "02-2-sub-2",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
}
|
|
]
|
|
},
|
|
"03": {
|
|
"v4_source": "tests/matching/v4_full32_result.yaml",
|
|
"aligned_section_ids": ["03-1", "03-2"],
|
|
"sections": [
|
|
{
|
|
"section_id": "03-1",
|
|
"candidate_status": "ok",
|
|
"candidates": [
|
|
{"template_id": "three_parallel_requirements", "label": "use_as_is", "confidence": 0.9268},
|
|
{"template_id": "dx_sw_necessity_three_perspectives", "label": "light_edit", "confidence": 0.8413}
|
|
]
|
|
},
|
|
{
|
|
"section_id": "03-2",
|
|
"candidate_status": "ok",
|
|
"candidates": [
|
|
{"template_id": "process_product_two_way", "label": "use_as_is", "confidence": 0.9198}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"04": {
|
|
"v4_source": "tests/matching/v4_full32_result.yaml",
|
|
"aligned_section_ids": ["04-1", "04-2-sub-1", "04-2-sub-2"],
|
|
"sections": [
|
|
{
|
|
"section_id": "04-1",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
},
|
|
{
|
|
"section_id": "04-2-sub-1",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
},
|
|
{
|
|
"section_id": "04-2-sub-2",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
}
|
|
]
|
|
},
|
|
"05": {
|
|
"v4_source": "tests/matching/v4_full32_result.yaml",
|
|
"aligned_section_ids": ["05-1", "05-2-sub-1", "05-2-sub-2"],
|
|
"sections": [
|
|
{
|
|
"section_id": "05-1",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
},
|
|
{
|
|
"section_id": "05-2-sub-1",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
},
|
|
{
|
|
"section_id": "05-2-sub-2",
|
|
"candidate_status": "no_non_reject_v4_candidate",
|
|
"candidates": []
|
|
}
|
|
]
|
|
}
|
|
}
|