dp-zp-agent/tools/graphrag/evaluation/results/final_v2_2026-10-25/summary.json
2026-10-25 02:06:17 +01:00

47 lines
1.2 KiB
JSON

{
"dev": {
"questions": 509,
"strict_count": 509,
"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": 0.042799,
"latency_median_seconds": 0.040359,
"latency_p95_seconds": 0.061584
},
"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
},
"unit_tests": {
"passed": 426,
"skipped": 4
},
"freeze_sha256": "233ce6fe63749b921d4c9947a55279ba5912fce0ff819153bfd6aaaf80910a46",
"limitations": "13 unseen-subject failures preserved; next version must use a new holdout."
}