Этап 4 / Пакет по РБП восстановление живого контура сбора данных и доказательной базы

2026-03-29 10:38:04 +03:00
parent 095e74ad3b
commit 133b6dca3c
83 changed files with 265742 additions and 77 deletions
@@ -0,0 +1,7 @@
+# Live Case Matrix
+
+| Case | Label | Reply | Claim Type | Admissible Evidence | Grounding Mode | Scope | Temporal |
+| --- | --- | --- | --- | ---: | --- | --- | --- |
+| L1 | vat_chain_furniture_13_15_july | factual_with_explanation | prove_vat_chain_completeness | 12 | grounded_positive | company_specific_accounting | passed |
+| L2 | rbp_tail_31_july_5000 | partial_coverage | prove_rbp_tail_state | 0 | limited_or_insufficient_evidence | company_specific_accounting | passed |
+| L3 | fa_amortization_2471_2465_849 | partial_coverage | prove_month_close_state | 19 | limited_or_insufficient_evidence | company_specific_accounting | passed |
@@ -0,0 +1,23 @@
+# Live Replay Report (Wave 19.2)
+
+## Source
+- Source of truth replayed from: `X:\1C\NDC_1C\llm_normalizer\docs\runs\2026-03-29_Stage_04_Wave_19_1_Live_Alignment_Fix_Claim_Bound_Runtime\1.txt`
+- Replayed exactly 3 user turns from the original export.
+- Runtime path: MCP ON, useMock=true.
+
+## Metrics
+- live_temporal_contradiction_rate: 0
+- live_company_scope_resolution_rate: 1
+- live_admissible_evidence_nonzero_rate: 0.6667
+- live_partial_coverage_default_rate: 0.6667
+- baseline_partial_coverage_default_rate: 1
+- live_claim_path_completion_rate: 0.6667
+- live_false_grounded_answer_rate: 0
+
+## Verdict
+- LIVE_TEMPORAL_ALIGNMENT_FIXED: FIXED
+- LIVE_COMPANY_SCOPE_FIXED: FIXED
+- LIVE_EVIDENCE_PATH_FIXED: FIXED
+- LIVE_PARTIAL_COVERAGE_DEFAULT_REDUCED: REDUCED
+- Overall: WAVE19_2_ACCEPTED
+
@@ -0,0 +1,6 @@
+{
+    "generated_at":  "2026-03-29T09:22:59",
+    "cases":  [
+
+              ]
+}
@@ -0,0 +1,36 @@
+{
+  "run_id": "2026-03-29_Stage_04_Wave_19_2_Live_Runtime_Fix_Replay_1txt",
+  "stage": "Stage_04",
+  "wave": "Wave_19_2",
+  "scope": "live_runtime_fix_by_replay_1txt",
+  "source_of_truth": "X:\\1C\\NDC_1C\\llm_normalizer\\docs\\runs\\2026-03-29_Stage_04_Wave_19_1_Live_Alignment_Fix_Claim_Bound_Runtime\\1.txt",
+  "execution": {
+    "replay_mode": "exact_questions_from_1_txt",
+    "runtime_path": "assistant_message_with_mcp_runtime_on",
+    "normalizer_mode": "useMock=true",
+    "session_id": "asst-wave19_2-1774763298275"
+  },
+  "thresholds": {
+    "live_temporal_contradiction_rate": 0,
+    "live_company_scope_resolution_rate": 1,
+    "live_false_grounded_answer_rate": 0,
+    "live_admissible_evidence_nonzero_min_cases": 2
+  },
+  "metrics": {
+    "case_count": 3,
+    "baseline_partial_coverage_default_rate": 1,
+    "live_temporal_contradiction_rate": 0,
+    "live_company_scope_resolution_rate": 1,
+    "live_admissible_evidence_nonzero_rate": 0.6667,
+    "live_partial_coverage_default_rate": 0.6667,
+    "live_claim_path_completion_rate": 0.6667,
+    "live_false_grounded_answer_rate": 0
+  },
+  "verdicts": {
+    "LIVE_TEMPORAL_ALIGNMENT_FIXED": "FIXED",
+    "LIVE_COMPANY_SCOPE_FIXED": "FIXED",
+    "LIVE_EVIDENCE_PATH_FIXED": "FIXED",
+    "LIVE_PARTIAL_COVERAGE_DEFAULT_REDUCED": "REDUCED",
+    "overall_status": "WAVE19_2_ACCEPTED"
+  }
+}
@@ -0,0 +1,38 @@
+[
+    {
+        "case_id":  "L1",
+        "label":  "vat_chain_furniture_13_15_july",
+        "claim_type":  "prove_vat_chain_completeness",
+        "routes":  "store_canonical -\u003e hybrid_store_plus_live",
+        "business_scope_resolved":  "company_specific_accounting",
+        "resolved_time_anchor":  "2020-07-13",
+        "temporal_guard_outcome":  "passed",
+        "admissible_evidence_count":  12,
+        "grounding_mode":  "grounded_positive",
+        "reply_type":  "factual_with_explanation"
+    },
+    {
+        "case_id":  "L2",
+        "label":  "rbp_tail_31_july_5000",
+        "claim_type":  "prove_rbp_tail_state",
+        "routes":  "store_canonical -\u003e store_canonical",
+        "business_scope_resolved":  "company_specific_accounting",
+        "resolved_time_anchor":  "2020-07-31",
+        "temporal_guard_outcome":  "passed",
+        "admissible_evidence_count":  0,
+        "grounding_mode":  "limited_or_insufficient_evidence",
+        "reply_type":  "partial_coverage"
+    },
+    {
+        "case_id":  "L3",
+        "label":  "fa_amortization_2471_2465_849",
+        "claim_type":  "prove_month_close_state",
+        "routes":  "store_feature_risk -\u003e hybrid_store_plus_live",
+        "business_scope_resolved":  "company_specific_accounting",
+        "resolved_time_anchor":  "2020-07-31",
+        "temporal_guard_outcome":  "passed",
+        "admissible_evidence_count":  19,
+        "grounding_mode":  "limited_or_insufficient_evidence",
+        "reply_type":  "partial_coverage"
+    }
+]