Jens/geointel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

audit: establish accuracy phase 1 baseline

Browse Source
This commit is contained in:
Jens
2026-08-01 18:57:38 +02:00
parent 0c019bb22f
commit 3d442ef43f
48 changed files with 15390 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/accuracy-program/status.json
+261
View File
@@ -0,0 +1,261 @@
{
"schema_version": 1,
"program": "GeoIntel Accuracy Improvement Program",
"phase": "P1",
"generated_at": "2026-08-01T18:40:00+02:00",
"scope": {
"product": "Belgium and the Belgian North Sea",
"active_building_model_claim": "Mol/Kempen only, operator review required",
"national_building_validation": false
},
"baseline": {
"branch": "codex/geointel-accuracy-program",
"repository_commit": "0c019bb22f816db1e4b7a68379bcad08924d9a21",
"database_migration_head": "202607260001",
"phase1_mutation_scope": "audit tooling, tests, documentation and retained evidence only"
},
"phase1": {
"status": "complete",
"meaning": "The forensic inventory, reproducible baseline, lineage assessment, risk register, metric contract, implementation roadmap and retained evidence exist.",
"does_not_mean": [
"release ready",
"nationally validated",
"human-reviewed corpus",
"strictly independent protected test",
"calibrated confidence",
"fully trained"
]
},
"release": {
"status": "blocked",
"promotion_allowed": false,
"scope_widening_allowed": false,
"training_allowed_now": false,
"training_unlock_gate": "P2-08 after P2-00 through P2-07 have passed",
"critical_risk_count": 8,
"high_risk_count": 17,
"medium_risk_count": 4
},
"phase2": {
"status": "ready_for_controlled_remediation",
"roadmap": "docs/accuracy-program/06-implementation-roadmap.md",
"first_work_package": "P2-00",
"required_order": [
"P2-00",
"P2-01",
"P2-02",
"P2-03",
"P2-04",
"P2-05",
"P2-06",
"P2-07",
"P2-08",
"P2-09",
"P2-10",
"P2-11",
"P2-12"
],
"protected_test_rule": "Open exactly once for a pre-registered immutable candidate after all pre-test gates pass; never feed its results back into that candidate family."
},
"runtime": {
"cuda_available": true,
"device": "NVIDIA GeForce RTX 4080 SUPER",
"configured_device": "cuda:0",
"python": "3.11.2",
"torch": "2.11.0+cu128",
"cuda_runtime": "12.8",
"ultralytics": "8.4.99",
"active_model": {
"model_id": "yolo-configured",
"model_version": "",
"path": "/app/models/geointel-building-yolov8s-smallbld-minpx3-img640-ft30.pt",
"sha256": "a9088b8491dfae36694b53e9e9406cb4e3511d334a5712fa34f75078a47759c1",
"size_bytes": 22516074,
"validated_area_names": [
"Mol",
"Kempen"
],
"nationally_validated": false
},
"gpu_smoke": {
"status": "passed",
"read_only": true,
"tile_crs": "EPSG:31370",
"tile_sha256": "134a9e86850c92c577c73bc6ee57a9df7d4c1c513ae6450263e800b6dd47b6ee",
"manifest_sha256": "6ab8a96bf2a1405e224932afb90255311a09bbeaed4e9a2fdcdf8b1bc2230abd",
"raw_detection_count": 17,
"inference_seconds": 0.8836944859940559,
"claim_boundary": "Runtime execution only; no accuracy, calibration, generalization or release claim."
}
},
"database": {
"mode": "read_only_audit",
"storage_references_checked": 5816,
"storage_references_missing": 0,
"table_counts": {
"projects": 1097,
"areas": 387,
"datasets": 3377,
"dataset_versions": 1671,
"vector_features": 6689447,
"analysis_runs": 1146,
"detections": 299233,
"segmentations": 0,
"detection_reviews": 0,
"quality_checks": 697,
"metrics": 4182,
"jobs": 4460,
"exports": 768,
"aoi_operations": 4,
"aoi_operation_partitions": 61
},
"lineage_gaps": {
"datasets_missing_observed_at": 2377,
"datasets_missing_source_version": 1761,
"detection_runs_with_empty_model_version": 1146,
"detections_with_empty_model_version": 299233,
"detection_runs_missing_model_hash": 3,
"detection_runs_missing_tile_manifest_hash": 1146
},
"geometry": {
"areas_invalid_or_wrong_srid": 0,
"vector_features_invalid_or_wrong_srid": 0,
"detections_outside_epsg4326_domain": 4,
"outside_domain_interpretation": "Four Geel detections contain Lambert-domain coordinates while persisted under SRID 4326."
}
},
"ml_data": {
"model_asset_count": 26,
"training_checkpoint_count": 229,
"training_json_report_count": 424,
"operator_manifest_count": 36,
"v56": {
"sample_count": 180,
"reviewed_sample_count": 0,
"review_complete": false,
"input_feature_count": 31452,
"accepted_feature_count": 30662,
"below_resolvable_pixel_size": 326,
"created_after_imagery_period": 464,
"pure_empty_background_count": 3,
"pure_empty_background_by_region": {
"flanders": 2,
"wallonia": 1,
"brussels": 0
},
"minimum_cross_split_aoi_distance_m": 95.72033647650719,
"cross_split_pairs_below_2000_m": 24,
"exact_cross_split_raster_hash_duplicates": 0,
"perceptual_pairs_hamming_at_or_below_4": 0,
"split_independence_proven": false
},
"candidate_evidence": {
"v58_v62_kind": "calibration-only tile-level bbox metrics",
"threshold_0_15_aggregate_f1": 0.512905360688286,
"threshold_0_15_flanders_recall": 0.0,
"protected_test_evidence": false,
"background_test_release_evidence": false,
"promotion_evidence": false
},
"protected_test_isolation": false,
"human_label_acceptance": false
},
"verification": {
"backend_full_suite": {
"status": "failed",
"passed": 1180,
"failed": 17,
"duration_seconds": 70.63,
"classification": "stale source/contract assertions; no new audit-tooling failures"
},
"backend_ci_entrypoint": {
"status": "collection_failed",
"collected": 1194,
"error": "ModuleNotFoundError: scripts.render_operator_polygon_label_qa"
},
"phase1_tooling_tests": {
"status": "passed",
"passed": 4
},
"new_phase1_code_ruff": {
"status": "passed"
},
"repository_ruff": {
"status": "failed",
"finding_count": 112,
"by_code": {
"E402": 13,
"E701": 2,
"E702": 69,
"F401": 23,
"F403": 1,
"F811": 2,
"F841": 2
}
},
"frontend_unit": {
"status": "passed",
"test_files": 16,
"tests": 51,
"command": "npm run test:unit"
},
"frontend_typecheck": {
"status": "passed"
},
"frontend_build": {
"status": "passed"
},
"frontend_lint": {
"status": "missing",
"error": "npm run lint: Missing script"
},
"openapi_contract": {
"status": "passed",
"implemented_routes": 147,
"explicit_non_envelope_endpoints": 10
},
"alembic": {
"status": "passed_offline",
"heads": [
"202607260001"
],
"offline_upgrade_sql_lines": 496,
"live_migration_tested_locally": false
},
"golden_qa": {
"semantic_results_stable": true,
"byte_identical": false,
"reason": "UUID4-backed run identity"
}
},
"reproduced_contract_violations": [
"P1-COV-001",
"P1-CRS-001",
"P1-CRS-002",
"P1-AUTH-001",
"P1-AI-001",
"P1-COV-002",
"P1-API-001"
],
"critical_blockers": [
"ACC-R01",
"ACC-R02",
"ACC-R03",
"ACC-R04",
"ACC-R06",
"ACC-R09",
"ACC-R16",
"ACC-R17"
],
"documents": [
"docs/accuracy-program/00-execution-contract.md",
"docs/accuracy-program/01-system-inventory.md",
"docs/accuracy-program/02-data-lineage.md",
"docs/accuracy-program/03-baseline-and-gaps.md",
"docs/accuracy-program/04-risk-register.md",
"docs/accuracy-program/05-metric-framework.md",
"docs/accuracy-program/06-implementation-roadmap.md"
],
"evidence_root": "artifacts/evidence/accuracy/P1",
"evidence_manifest": "artifacts/evidence/accuracy/P1/evidence-manifest.json"
}