root/Jyotisha
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

research(rectification): add reported-offset evaluation and frozen rerun integrity
Independent Staging Quality Gate / validate (push) Successful in 12m7s
Details
Independent Staging Quality Gate / publish (push) Successful in 3m46s
Details

Browse Source 
Preserve closed confirmation gates and previously-exposed dataset boundaries. Add auditable 900-trial sensitivity results, current scorer freshness checks, and the v5 collection protocol.

Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
jesse-ux
2026-09-20 12:03:52 +08:00
co-authored by Claude Code
parent 5049e7847b
commit 932f2fffba
22 changed files with 14134 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_rectification_confirmation_and.py
+5 -1
View File
@@ -93,6 +93,7 @@ def test_sealed_holdout_contract_matches_v3_report_and_stays_closed() -> None:
sidecar = diagnostic["current_tree_unfrozen_diagnostic"]
produced_by = product["metrics_produced_by"]
current_tree = product["current_tree_scorer"]
rerun = json.loads((ROOT / current_tree["source_report"]).read_text(encoding="utf-8"))
unfrozen = product["current_tree_unfrozen_diagnostic"]
assert holdout["sealed_benchmark_id"] == report["benchmark_id"] == product["sealed_benchmark_id"]
assert holdout["valid_public_aa_cases"] == report["validation"]["valid_public_aa_cases"]
@@ -115,7 +116,10 @@ def test_sealed_holdout_contract_matches_v3_report_and_stays_closed() -> None:
assert produced_by["algorithm_version"] == report["frozen_scoring"]["algorithm_version"]
assert produced_by["implementation_hash_matches_at_replay"] is True
assert produced_by["source_report"] == "references/real_case_calibration/minute_rectification_holdout_v3_report.json"
assert current_tree["implementation_sha256"] == diagnostic["frozen_scoring"]["actual_sha256"]
assert current_tree["implementation_sha256"] == rerun["frozen_record"]["implementation_sha256"]
assert current_tree["fixed_protocol_rerun_hash_matches"] is rerun["implementation_hash_matches_at_replay"] is True
assert current_tree["fixed_protocol_rerun_trial_count"] == rerun["trial_count"] == 20
assert rerun["official_valid_independent_blind"] is False
assert current_tree["matches_metrics_scorer"] is False
assert current_tree["official_eval_implementation_hash_matches"] is False
assert current_tree["official_eval_trial_count"] == diagnostic["trial_count"] == 0