Add date-isolated caches and regression coverage, align scoring identity, and freeze full research reruns while preserving historical artifacts. Record unresolved cache/receipt identity and end-to-end acceptance gaps for branch review only. Co-Authored-By: Claude Code <noreply@anthropic.com>
259 lines
8.7 KiB
JSON
259 lines
8.7 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"scope": "candidate_local_date_fix_not_product_accuracy_or_independent_blind_validation",
|
|
"baseline_commit": "03cba4780a220b132cf4f06d22e14608aaf9ad3c",
|
|
"baseline_source_sha256": {
|
|
"scripts/rectification/dasha_transition_proximity.py": "190c615d9733f4ca0cd2a903f67ecaa45afc1db3eaa0f72a6884d9fe5582b57b",
|
|
"scripts/rectification/scoring_service.py": "e0b3dbefbf501c20b1cd0d7353bdc3314ec98982c04164af003fa747295a09db"
|
|
},
|
|
"current_source_sha256": {
|
|
"scripts/rectification/dasha_transition_proximity.py": "0afba494aa12899621173c3cc941c6c1d0be9cec0bdf4c4a1c9bcd004ab22de8",
|
|
"scripts/rectification/scoring_service.py": "0adf5700bb22dd8c4c3147027251210e21ec66a2c9f9a91217edba3ad9e5d1f5"
|
|
},
|
|
"dataset_sha256": "45aa76ab79dfc6c6404b6252083e1aa5c7e2e2b7de811fc11042a8ad2da3f0ea",
|
|
"parameters": {
|
|
"dataset": "references/real_case_calibration/minute_rectification_holdout_v3.json",
|
|
"public_aa_case_count": 20,
|
|
"radius_minutes": 60,
|
|
"offset_minutes": 0,
|
|
"minute_step": 1,
|
|
"candidates_per_window": 121,
|
|
"ayanamsa": "raman",
|
|
"node_mode": "mean",
|
|
"timed_scope": "compute_candidate_static_contexts + build_event_contribution_matrix + score_from_matrix",
|
|
"timing_method": "same process, five alternating baseline/fixed pairs; baseline helper preserved before modification; all other scoring paths identical",
|
|
"score_serialization": "json.dumps(scores, sort_keys=True, separators=(\",\", \":\")).encode()",
|
|
"matrix_comparison": "same canonical JSON serialization then SHA-256",
|
|
"timing_pair_orders": [
|
|
"baseline,fixed",
|
|
"fixed,baseline",
|
|
"baseline,fixed",
|
|
"fixed,baseline",
|
|
"baseline,fixed"
|
|
]
|
|
},
|
|
"timing": {
|
|
"pre_fix_samples_seconds": [
|
|
22.780348100000992,
|
|
21.738976600026945,
|
|
20.851636399980634
|
|
],
|
|
"paired_alternating_samples_seconds": {
|
|
"baseline": [
|
|
27.478544100013096,
|
|
21.569872399995802,
|
|
20.71335249999538,
|
|
21.362332899996545,
|
|
21.438496799994027
|
|
],
|
|
"fixed": [
|
|
21.150953400006983,
|
|
21.252369000023464,
|
|
20.739417499979027,
|
|
21.42927980000968,
|
|
21.525520600000164
|
|
]
|
|
},
|
|
"paired_median_seconds": {
|
|
"baseline": 21.438496799994027,
|
|
"fixed": 21.252369000023464
|
|
},
|
|
"median_change_percent": -0.868194266169886,
|
|
"paired_change_percent": [
|
|
-23.027387029588287,
|
|
-1.4719762550491455,
|
|
0.1258367035642971,
|
|
0.3133875889236082,
|
|
0.40592304963360526
|
|
],
|
|
"maximum_allowed_regression_percent": 20
|
|
},
|
|
"same_day": {
|
|
"case_count": 19,
|
|
"candidate_count": 2299,
|
|
"comparisons": [
|
|
{
|
|
"case_ordinal": 1,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "2aabdda6bb56baf6a9d0b119964ee1ab8023fede9ea8703f6d265207c490bec2"
|
|
},
|
|
{
|
|
"case_ordinal": 2,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "6585d895aeb79e26257b1002696c16b5e252f9a702f2a5702f929fd80486abb9"
|
|
},
|
|
{
|
|
"case_ordinal": 3,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "246296903d915e4886229530fa554428d7f65fb686f70cc369711347ebaf2610"
|
|
},
|
|
{
|
|
"case_ordinal": 4,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "79126128e3a9e861c076569428729cd490f6a122aa35e33975066533e1cc08f0"
|
|
},
|
|
{
|
|
"case_ordinal": 5,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "3f891b16ae23d499a676610829e240ded987cc32570c81ac9e2f24f09ab5cae1"
|
|
},
|
|
{
|
|
"case_ordinal": 7,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "d211367fac590c19d6b68e7717fa605ab70fa0c2f9c7adda2477f211a909de77"
|
|
},
|
|
{
|
|
"case_ordinal": 8,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "1e5a0d58160f7bea190cff621acfaf7e94f82a8b64c2ab2a7b16d574fa72545f"
|
|
},
|
|
{
|
|
"case_ordinal": 9,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "8673a519a9729194e44305bfa329092f0e5fec2b21c5cea8c0271136a610c22c"
|
|
},
|
|
{
|
|
"case_ordinal": 10,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "3525cfcee8c541ac707c83b7badcb1c1c990ffa93c220d17ad95df79fd272ffb"
|
|
},
|
|
{
|
|
"case_ordinal": 11,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "3224140f8f1d5bfa76727a77b17859751a384c3ee45dbff07f9b3e073431c488"
|
|
},
|
|
{
|
|
"case_ordinal": 12,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "4ad82e9d8d9af710078906deb0c82c2d11cccb7b85051d769db48c952c633ef1"
|
|
},
|
|
{
|
|
"case_ordinal": 13,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "ae7e7a6282f6130d8769d52dbf419b16434ac6b27c166ebacab8cb2ae03ae905"
|
|
},
|
|
{
|
|
"case_ordinal": 14,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "02319206460876de38170308930896142171595636ffffef9bfe652b3760c089"
|
|
},
|
|
{
|
|
"case_ordinal": 15,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "d29d0098f63db390f8de05abba77d88b5f5f2d3d63deebf12f1edecad1935e3d"
|
|
},
|
|
{
|
|
"case_ordinal": 16,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "a9ef128d8535171bfd55ebb30ee7a6f5137f40f3a38218de691f2259d4ee8e1f"
|
|
},
|
|
{
|
|
"case_ordinal": 17,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "675f400eb0ef8840092fb512de62ca29eb0482065178ccb0f8d1020b38f4b168"
|
|
},
|
|
{
|
|
"case_ordinal": 18,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "d17e6197a5ef668130e72d6513ebacb7ce357d27b7569d6be29be8dcd3f52dff"
|
|
},
|
|
{
|
|
"case_ordinal": 19,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "a0bb50c9e7a6b48c9206a486e0962271129489ff53a2ee76ff827fcba52a480b"
|
|
},
|
|
{
|
|
"case_ordinal": 20,
|
|
"candidate_count": 121,
|
|
"scores_bytes_equal": true,
|
|
"matrix_bytes_equal": true,
|
|
"scores_sha256": "183324931666a285b04624facd50cc1adc82f7a50ba41f3cb1765695469507c0"
|
|
}
|
|
]
|
|
},
|
|
"cross_day": {
|
|
"case_ordinal": 6,
|
|
"method": "natural cross-midnight window, independent single-candidate matrices each anchored to its own local date, compare all rows and cells",
|
|
"baseline": {
|
|
"candidate_count": 121,
|
|
"cross_date_candidates": 16,
|
|
"different_candidate_count": 16,
|
|
"same_day_different_count": 0,
|
|
"max_absolute_score_delta": 0.0267,
|
|
"full_rows_equal": false,
|
|
"full_matrix_equal": false
|
|
},
|
|
"fixed": {
|
|
"candidate_count": 121,
|
|
"cross_date_candidates": 16,
|
|
"different_candidate_count": 0,
|
|
"same_day_different_count": 0,
|
|
"max_absolute_score_delta": 0.0,
|
|
"full_rows_equal": true,
|
|
"full_matrix_equal": true
|
|
}
|
|
},
|
|
"tests": {
|
|
"pre_fix": {
|
|
"failed": 4,
|
|
"passed": 4,
|
|
"elapsed_seconds": 7.32
|
|
},
|
|
"post_fix_with_quick_bridge": {
|
|
"failed": 0,
|
|
"passed": 18,
|
|
"elapsed_seconds": 14.71,
|
|
"unique_test_count": 9
|
|
},
|
|
"existing_endpoint_registry_enumeration": {
|
|
"failed": 0,
|
|
"passed": 3,
|
|
"elapsed_seconds": 0.69
|
|
},
|
|
"quick_bridge_collected": 9,
|
|
"notes": "Version identity regression added after red run; bridge repeats the same nine regressions. Full quick and broad baseline comparisons are coordinator-owned."
|
|
},
|
|
"scope_verification": {
|
|
"frozen_files_count": 12,
|
|
"frozen_files_unchanged": true,
|
|
"all_proximity_constants_unchanged": true
|
|
},
|
|
"privacy": "Only public dataset anonymous ordinals, score hashes and aggregates; no birth times, dates, names, coordinates, case IDs or raw scores."
|
|
}
|