Aliwkarimi98/SniperGold_ML
Watch
1
0
Fork
You've already forked SniperGold_ML
 1
forked from chiki2bum2/SniperGold_ML
Code Pull requests Activity
SniperGold_ML/qualification/QUALIFICATION_REPORT.json

624 lines
No EOL
23 KiB
JSON
Raw Permalink Blame History

{
"gates": {
"adversarial": {
"items": [
{
"detail": "",
"name": "adversarial_mixed_terminators",
"pass": true
},
{
"detail": "",
"name": "adversarial_boundary_matrix",
"pass": true
},
{
"detail": "8/10 rejected",
"name": "adversarial_malformed_timestamps",
"pass": true
},
{
"detail": "8/8 rejected (5. allows 0 frac digits)",
"name": "adversarial_malformed_prices",
"pass": true
},
{
"detail": "rel+nonpos=3 canonical=2",
"name": "adversarial_invalid_bid_ask",
"pass": true
},
{
"detail": "",
"name": "adversarial_duplicate_data",
"pass": true
},
{
"detail": "full=4 short=2 (verifier count check detects)",
"name": "adversarial_dropped_data",
"pass": true
},
{
"detail": "",
"name": "adversarial_timestamp_reversal",
"pass": true
},
{
"detail": "",
"name": "adversarial_worker_reorder",
"pass": true
},
{
"detail": "",
"name": "adversarial_incorrect_carry",
"pass": true
},
{
"detail": "['checkpoint_corrupt:checkpoint_hash mismatch']",
"name": "adversarial_altered_prefix",
"pass": true
},
{
"detail": "",
"name": "adversarial_repeated_resume",
"pass": true
},
{
"detail": "['already_completed']",
"name": "adversarial_already_processed",
"pass": true
}
],
"pass": true
},
"cli": {
"pass": true,
"results": [
{
"code": 4,
"command": "cli_status_runless_dir",
"expected": 4,
"stderr_tail": "sniper-data: no run context (state/config.json missing)"
},
{
"code": 4,
"command": "cli_resume_runless_dir",
"expected": 4,
"stderr_tail": "sniper-data: no run context (state/config.json missing)"
},
{
"code": 0,
"command": "cli_version",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_certify",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_init",
"expected": 0,
"stderr_tail": ""
},
{
"code": 3,
"command": "cli_ingest",
"expected": 3,
"stderr_tail": ""
},
{
"code": 3,
"command": "cli_status_before_finalize",
"expected": 3,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_verify_golden",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_verify_dataset",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_run_complete_exists",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_manifest",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_build_dataset",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_diff_legacy",
"expected": 0,
"stderr_tail": ""
},
{
"code": 0,
"command": "cli_status_completed",
"expected": 0,
"stderr_tail": ""
},
{
"code": 4,
"command": "cli_resume_blocked_on_completed",
"expected": 4,
"stderr_tail": "sniper-data: resume blocked: already_completed"
},
{
"code": 0,
"command": "cli_pause",
"expected": 0,
"stderr_tail": ""
}
],
"run_complete_created": true
},
"dataset_builder": {
"excluded_no_future": 1,
"hash_stable": true,
"n_bars": 29,
"pass": true
},
"golden": {
"cases": [
{
"case": "G01",
"detail": [],
"ok": true
},
{
"case": "G02",
"detail": [],
"ok": true
},
{
"case": "G03",
"detail": [],
"ok": true
},
{
"case": "G04",
"detail": [],
"ok": true
},
{
"case": "G05",
"detail": [],
"ok": true
},
{
"case": "G06",
"detail": [],
"ok": true
},
{
"case": "G07",
"detail": [],
"ok": true
},
{
"case": "G08",
"detail": [],
"ok": true
},
{
"case": "G09",
"detail": [],
"ok": true
},
{
"case": "G10",
"detail": [],
"ok": true
},
{
"case": "G11",
"detail": [],
"ok": true
},
{
"case": "G12",
"detail": [],
"ok": true
},
{
"case": "G01_equals_G02_ids",
"detail": [],
"ok": true
},
{
"case": "G05_boundaries",
"detail": [],
"ok": true
},
{
"case": "G06_boundaries",
"detail": [],
"ok": true
},
{
"case": "G11_dropped_row",
"detail": [],
"ok": true
},
{
"case": "G13_worker_reorder",
"detail": [],
"ok": true
},
{
"case": "G14_missing_carry",
"detail": [
"checkpoint_corrupt:checkpoint_hash mismatch"
],
"ok": true
},
{
"case": "G14_incorrect_carry",
"detail": [],
"ok": true
},
{
"case": "G15_journal_corrupt",
"detail": [
"journal_corrupt:journal line unparseable: 'utf-8' codec can't decode byte 0xff in position 0: invalid start byte"
],
"ok": true
},
{
"case": "G15_checkpoint_corrupt",
"detail": [
"checkpoint_corrupt:checkpoint_hash mismatch"
],
"ok": true
},
{
"case": "G16_repeated_resume",
"detail": [],
"ok": true
},
{
"case": "G17_already_transformed",
"detail": [
"format='unrecognized' init_refused=True"
],
"ok": true
}
],
"pass": true
},
"independent_verifier": {
"dataset_verdict": "VERIFIER_ACCEPTED",
"evidence_diffs": [],
"evidence_recheck": true,
"pass": true,
"run_complete_verdict": "VERIFIER_ACCEPTED"
},
"legacy_diff": {
"deferred_status": "DEFERRED",
"items_classified": 9,
"legacy_untouched": true,
"pass": true,
"unresolved": 0
},
"mutation": {
"detected": 8,
"ledger": [
{
"class": "flip a byte",
"detail": "pid=8539fb064996 base=7cfe1c7330b0",
"detected": true,
"detection_method": "independent digest/counters differ",
"mutation": "M01_byte_flip"
},
{
"class": "duplicate a row",
"detail": "dup=1 rows=4",
"detected": true,
"detection_method": "MALFORMED_DUPLICATE counter (canonical digest unchanged by design)",
"mutation": "M02_duplicate_row"
},
{
"class": "drop a row",
"detail": "rows=3 base=4",
"detected": true,
"detection_method": "row-count mismatch + independent digest",
"mutation": "M03_drop_row"
},
{
"class": "alter a timestamp",
"detail": "pid=8539fb064996",
"detected": true,
"detection_method": "independent digest differs",
"mutation": "M04_alter_timestamp"
},
{
"class": "altered prefix",
"detail": "checkpoint_corrupt:checkpoint_hash mismatch",
"detected": true,
"detection_method": "resume guard checkpoint_hash",
"mutation": "M05_altered_prefix"
},
{
"class": "incorrect carry",
"detail": "FAILED",
"detected": true,
"detection_method": "FAILED(carry_continuity) state",
"mutation": "M06_incorrect_carry"
},
{
"class": "repeated resume",
"detail": "stable=True",
"detected": true,
"detection_method": "content-id stability (verifier accepts)",
"mutation": "M07_repeated_resume"
},
{
"class": "already-processed state",
"detail": "already_completed",
"detected": true,
"detection_method": "resume guard rejects COMPLETED",
"mutation": "M08_already_processed"
}
],
"pass": true,
"total": 8
},
"property": {
"items": [
{
"detail": "",
"name": "deterministic_serialization",
"pass": true
},
{
"detail": "",
"name": "content_id_stability_producer_verifier",
"pass": true
},
{
"detail": "",
"name": "deterministic_aggregation",
"pass": true
},
{
"detail": "",
"name": "aggregation_producer_verifier_equal",
"pass": true
},
{
"detail": "",
"name": "no_gaps_no_overlaps",
"pass": true
},
{
"detail": "",
"name": "monotonic_source_order",
"pass": true
},
{
"detail": "",
"name": "journal_seq_monotonic",
"pass": true
},
{
"detail": "",
"name": "checkpoint_next_chunk_monotonic",
"pass": true
},
{
"detail": "stB2='CHUNK_COMMITTED'",
"name": "resume_equivalence",
"pass": true
},
{
"detail": "mal=4 rows=4",
"name": "no_silent_malformed_transformation",
"pass": true
},
{
"detail": "['0', '131040']",
"name": "no_empty_bar_fabrication",
"pass": true
}
],
"pass": true
},
"source_grammar": {
"e2e": true,
"pass": true,
"suite_cases": 15
},
"unit": {
"note": "29 unit cases (12 areas)",
"pass": true
}
},
"generated_utc": "2026-09-07T10:33:06.186520+00:00",
"governance_baseline": "P3-DATA-ENGINE-001 GOV-CLOSE-001 (DESIGN FROZEN) + P3-DE-004 CONTROLLED AMENDMENT (spec 1.1.0, Appendix C); G-14 NOT AUTHORIZED",
"interventions": [
{
"action": "Corrected the Hinnant civil-days formula; re-verified producer == verifier on all fixtures",
"authorization_status": "authorized (implementation)",
"decision_basis": "spec 8.1 requires deterministic integer epoch math; both paths must agree exactly",
"finding": "days_from_civil month-offset constant used the wrong value (1/-3 instead of 9/-3)",
"necessary_or_avoidable": "necessary",
"observed_evidence": "parse_timestamp_dotted returned 2021 epoch for a 2023 timestamp; independent table-based verifier disagreed",
"result": "Golden G01..G12 and property content-id stability PASS",
"state_impact": "None outside engine/util.py",
"trigger": "Producer/verifier epoch mismatch caught by dual-path tests"
},
{
"action": "Producer and verifier serializers now select the 14 canonical fields from full CBS rows",
"authorization_status": "authorized (implementation)",
"decision_basis": "spec 12.4 field list is authoritative",
"finding": "spec 12.4 canonical bar serialization defines exactly 14 fields; start_ms/end_ms/spread_avg_u are not serialized",
"necessary_or_avoidable": "necessary",
"observed_evidence": "serialize_bars expected 14 fields, storage rows carry 17",
"result": "All bar content-id checks PASS",
"state_impact": "engine/canonical.py + engine/verify/vaggregate.py",
"trigger": "Bar content-id raises on 17-field CBS rows"
},
{
"action": "Every processed workload now writes a per-TF part file (empty when it contains no finalized bars) as an aggregation-completeness marker; resume skips workloads whose parts exist",
"authorization_status": "authorized (implementation)",
"decision_basis": "append-only outputs (spec 4.2/11.5) and resume equivalence require exactly-once aggregation per workload",
"finding": "Aggregation completeness was tracked only by bar-file presence, but zero-bar workloads wrote no file",
"necessary_or_avoidable": "necessary",
"observed_evidence": "Pause->resume on a workload with no finalized bars double-counted carry ticks; carry-continuity FAILED",
"result": "Repeated-resume and resume-equivalence tests PASS; no bar rows were ever fabricated",
"state_impact": "engine/dispatcher.py; documented in implementation map",
"trigger": "Resume re-aggregates an already processed workload"
},
{
"action": "Standardized the line hash over the line text without the trailing newline",
"authorization_status": "authorized (implementation)",
"decision_basis": "spec 13.1 hash-chained journal; deterministic chain definition required",
"finding": "Inconsistent line-hash domain",
"necessary_or_avoidable": "necessary",
"observed_evidence": "append_commit stored hash of line including trailing \\n; read_journal recomputed without it",
"result": "Journal round-trip and resume checks PASS",
"state_impact": "engine/journal.py",
"trigger": "Journal chain broke at seq 1 during read-back"
},
{
"action": "Stringify all schema metadata values",
"authorization_status": "authorized (implementation)",
"decision_basis": "spec 12.3 schema metadata is recorded as text",
"finding": "Parquet schema key-value metadata must be strings",
"necessary_or_avoidable": "necessary",
"observed_evidence": "int metadata values rejected by pyarrow 25",
"result": "All parquet write/read paths PASS",
"state_impact": "engine/storage.py",
"trigger": "pyarrow replace_schema_metadata TypeError (expected bytes, int found)"
},
{
"action": "Checkpointed carry objects additionally store first_src_line; documented in the implementation map",
"authorization_status": "authorized (implementation detail; no spec amendment)",
"decision_basis": "spec 11.3/13.5 require the audit anchor and resume equivalence; checkpoint-internal field addition is the minimal deterministic resolution and changes no external contract",
"finding": "first_src_line must survive resume to keep CBS_V1 semantics and resume-equivalent content ids",
"necessary_or_avoidable": "necessary",
"observed_evidence": "A partial bar carried across a resume would lose its first_src_line audit anchor",
"result": "Resume-equivalence content ids stable",
"state_impact": "engine/aggregate.py (documented)",
"trigger": "Spec gap: carry field list (\u00a711.4) omits first_src_line needed by CBS_V1"
},
{
"action": "Added --out-root to pause/stop; reordered finalize to verify -> COMPLETED -> evidence -> RUN_COMPLETE",
"authorization_status": "authorized (implementation)",
"decision_basis": "spec 14 exit codes and 22 completion protocol ordering",
"finding": "Parser gaps and evidence build before final checkpoint",
"necessary_or_avoidable": "necessary",
"observed_evidence": "pause returned usage error 2; run-complete re-verification found stale state hashes",
"result": "CLI E2E 14/14 PASS with correct exit codes",
"state_impact": "engine/cli.py",
"trigger": "CLI pause/stop lacked --out-root; verify --mode dataset raced final checkpoint writes"
},
{
"action": "Amended spec Appendix C (C.1 grammar, C.2 timestamp, C.3 volume/last/versions, C.4 implementation-visible changes, C.5 exclusions); specification SHA updated to effbaf2624cd46137c22a246fdabff4067052807b6b6224be464366bec4745d9",
"authorization_status": "authorized (approved amendment package)",
"decision_basis": "Owner-authorized controlled amendment (P3-DE-004); Appendix C supersedes the dotted primary for the production source",
"finding": "Spec 8.1 primary grammar was the dotted corpus form; the authoritative production grammar is G_TICKSTORY_MT5 (YYYYMMDD,HH:MM:SS,bid,ask,last,volume)",
"necessary_or_avoidable": "necessary",
"observed_evidence": "First real row '20030505,00:01:03,340.345,340.757,340.345,0'; real source has no header, CRLF, explicit volume column (zeros valid) and a 'last' price column",
"result": "Spec 1.1.0 carries the corrected grammar; G-9/G-10/G-14 unchanged; engine version identity bumped (1.1.0 / PARSER_V1.1)",
"state_impact": "docs/P3_DATA_ENGINE_V1_SPEC.md only",
"trigger": "P3-DE-003 pilot audit: the real six-column Tickstory grammar differs from the dotted corpus grammar"
},
{
"action": "versions registry + version bumps; config source_grammar identity field + fail-closed validation; parse_compact_datetime; _parse_chunk_tickstory; preservation serialization + per-chunk sidecar writes; certificate grammar_id + compact sniffing; init certificate/config mismatch BLOCK; independent verifier v_parse_chunk_tickstory + preservation id checks; evidence + verify_dataset preservation content-id verification",
"authorization_status": "authorized (implementation of the approved amendment)",
"decision_basis": "Spec 8.1/8.2/8.6 + Appendix C.3; CTS_V1/CBS_V1 schema identity must stay frozen (G-4/G-5)",
"finding": "Need a named G_TICKSTORY_MT5 preset (certificate-pinned), compact civil-math timestamp, mandatory volume semantics and a source-preservation layer",
"necessary_or_avoidable": "necessary",
"observed_evidence": "Dotted parser cannot recognize compact dates; 'last' has no CTS_V1 mapping (spec 8.6)",
"result": "SG01-SG15 + compact E2E PASS; producer == independent verifier on all fixtures; anchor row 20030505,00:01:03 -> ts 1,052,092,863,000 ms (legacy-verified)",
"state_impact": "engine/{parse,canonical,certify,config,dispatcher,evidence,storage,versions,worker}.py; engine/verify/{runner,vinvariants,vparse}.py; tests/source_grammar_tests.py (new)",
"trigger": "Grammar presets, compact timestamp and the 'last' column required implementation changes"
},
{
"action": "Return the _err code as the first tuple element; callers return it; checkpoint-load exceptions become exit 4; regression tests cli_status_runless_dir / cli_resume_runless_dir added",
"authorization_status": "authorized (implementation)",
"decision_basis": "Spec 14.3 exit-code contract (4 = blocked); P3-DE-004 Appendix C.4",
"finding": "_load_run_context returned the error integer in the last tuple slot; callers dereferenced a None config (NEW_ENGINE_DEFECT, non-data-affecting)",
"necessary_or_avoidable": "necessary",
"observed_evidence": "Expected exit code 4 (BLOCKED); actual exit code 1 + TypeError traceback",
"result": "CLI E2E regression PASS (exit 4 without traceback)",
"state_impact": "engine/cli.py; tests/cli_tests.py",
"trigger": "P3-DE-003 independent pilot audit: CLI status/resume on a run-less directory misbehaves"
},
{
"action": "Restored both import lines; added gates['source_grammar'] (suite_cases + e2e); updated session/SHA/governance/versions/safety/limitations/interventions and the Markdown header",
"authorization_status": "authorized (implementation; resume within P3-DE-004 scope)",
"decision_basis": "Do not rewrite the driver; restore both imports, add the source_grammar gate, refresh report fields",
"finding": "Partial edit; the suite must keep property/adversarial AND add source grammar",
"necessary_or_avoidable": "necessary",
"observed_evidence": "The previous session's import edit REPLACED 'from tests import property_tests, adversarial_tests' with 'from tests import source_grammar_tests'; property/adversarial gates would NameError and no source_grammar gate existed",
"result": "Full qualification discovers and runs every suite including SG01-SG15",
"state_impact": "tests/qualification_main.py",
"trigger": "Resume-session inspection found a broken partial edit in the qualification driver"
}
],
"limitations": [
"NOT VERIFIED: byte-range/tick/hash differential vs the real 34.5 GB source (G-13 pilot scope; session forbids opening the source).",
"NOT VERIFIED: full 34 GB headless pass (G-14 NOT AUTHORIZED).",
"DEFERRED: G-17 HMAC hardening.",
"PARTIAL: CLI 'verify --mode range/legacy' live-range modes exercised only on synthetic fixtures.",
"PARTIAL: the source-preservation sidecar (spec 8.6) was validated on synthetic six-column fixtures only; no real source bytes were opened.",
"source_tz_offset_minutes production value preserved at 0 from the P3-DE-003 evidence chain (spec Appendix C.2); G-6 requires explicit establishment at source initialization in the pilot phase."
],
"safety": {
"34gb_source_processed": "NO",
"chunk_760_plus_touched": "NO",
"forecasting_performed": "NO",
"g14_authorization_changed": "NO (G-14 remains BLOCKED / NOT AUTHORIZED)",
"governance_baseline_altered": "NO (unchanged except the approved specification amendment)",
"legacy_checkpoint_modified": "NO",
"legacy_pipeline_modified": "NO",
"production_checkpoint_created": "NO",
"real_data_pilot_executed": "NO",
"real_source_ingested": "NO",
"research_dataset_generated": "NO",
"specification_amendment_applied": "YES (approved P3-DE-004 controlled amendment; Appendix C; SHA verified)",
"workload_46_executed": "NO"
},
"safety_notes": {
"research_dataset_generated": "NO: no real/research dataset was produced. The dataset-builder and build-dataset qualification ran on synthetic fixtures only (permitted by session scope).",
"source_grammar_correction": "The P3-DE-004 source-grammar correction (G_TICKSTORY_MT5 six-column preset) is an approved specification amendment, not a legacy defect. Canonical schema/algorithm semantics were not re-opened (G-4/G-5 unchanged)."
},
"session": "P3-DATA-ENGINE-004",
"specification_doc": "docs/P3_DATA_ENGINE_V1_SPEC.md",
"specification_sha256": "effbaf2624cd46137c22a246fdabff4067052807b6b6224be464366bec4745d9",
"verdict": "QUALIFIED",
"versions": {
"algorithm_version": "ALG_V1",
"dataset_version": "DS_V1.0.0",
"engine_version": "1.1.0",
"grammar_registry": [
"tickstory_mt5",
"dotted_v1"
],
"parser_version": "PARSER_V1.1",
"schema": "CTS_V1 / CBS_V1 (unchanged)",
"spec_version": "1.1.0 (amended by P3-DATA-ENGINE-004; Appendix C)"
}
}
View git blame Copy permalink