dp-zp-agent/tools/graphrag/evaluation/results/final_v3_2026-10-25/summary.json

79 lines
2.1 KiB
JSON

{
"version": "v3",
"dev": {
"questions": 589,
"strict_count": 589,
"strict_accuracy": 1.0,
"error_count": 0,
"value_score": 1.0,
"entity_score": 1.0,
"relation_score": 1.0,
"property_score": 1.0,
"relation_choice_score": 1.0,
"document_recall": 1.0,
"source_recall": 1.0,
"binding_score": 1.0,
"path_score": 1.0,
"answerability_accuracy": 1.0,
"latency_mean_seconds": 0.041531,
"latency_median_seconds": 0.040416,
"latency_p95_seconds": 0.056271
},
"test": {
"questions": 13,
"strict_count": 13,
"strict_accuracy": 1.0,
"error_count": 0,
"value_score": 1.0,
"entity_score": 1.0,
"relation_score": 1.0,
"property_score": 1.0,
"relation_choice_score": 1.0,
"document_recall": 1.0,
"source_recall": 1.0,
"binding_score": 1.0,
"path_score": 1.0,
"answerability_accuracy": 1.0,
"latency_mean_seconds": 0.054831,
"latency_median_seconds": 0.043193,
"latency_p95_seconds": 0.109367
},
"tests": {
"passed": 430,
"skipped": 4,
"neo4j_rollback_cases": 10
},
"freeze_sha256": "89731e4cc375e6c2a84759a4d7ec1db3f01f4a406be42c7a8d6df7ce27780ab1",
"independence": {
"source_profile_overlap": 0,
"test_profiles": 2,
"test_questions": 13,
"limitation": "Supplementary small holdout with limited category coverage; no universal 100% correctness claim."
},
"broader_v2_independent_test": {
"questions": 80,
"strict_count": 67,
"strict_accuracy": 0.8375,
"error_count": 0,
"value_score": 0.845833,
"entity_score": 0.84375,
"relation_score": 1.0,
"property_score": 1.0,
"relation_choice_score": 1.0,
"document_recall": 1.0,
"source_recall": 1.0,
"binding_score": 0.8375,
"path_score": 0.8375,
"answerability_accuracy": 0.8375,
"latency_mean_seconds": 0.046289,
"latency_median_seconds": 0.037556,
"latency_p95_seconds": 0.054178
},
"v2_test_now_development_only": true,
"legacy_137_resolution": {
"literal_tag_false_premises": 128,
"exact_category_corrections": 9
},
"post_test_python_changes": false
}