mirror of
https://github.com/allaunthefox/Research-Stack.git
synced 2026-07-31 03:05:21 +00:00
0c9efac330
Squash the four overlapping feature branches into a single change set against main, eliminating cross-PR merge conflicts and the duplicated CI-fix scripts. What this brings in (merge order #79 -> #80 -> #81 -> #89): - #79 refactor(infra): shared utilities (4-Infrastructure/lib/*: q16, hashing, jsonl, fraction_utils) + the scripts/math-first/* validators that the math-check CI requires. - #80 feat(lean): Semantics.E8Sidon (1025 lines) -- Eisenstein coefficient identity E4^2 = E8 and the Sidon framework. E4_sq_eq_E8_coeff is fully proved (all Fourier-coefficient extraction machine-checked); the single residual gap is pinned to E4_sq_eq_E8_qExpansion (Mathlib lacks the valence formula / dim M8 = 1). 4 sorries + 1 axiom (e8_additive_completeness), all TODO(lean-port). - #81 refactor(lean): Float-free FixedPoint core (integer-only sqrt/log2/expNeg). E8Sidon.lean kept at #80's final 1025-line version (the #81 intermediate 438-line copy was overridden by merge order). - #89 feat(lean): Semantics.RRC.PolyFactorIdentity -- short-sleeve polynomial detection at the zerocopy limb boundary; now imports Semantics.E8Sidon for sigma3/sigma7/convolutionLHS (single source of truth) instead of inlining them. Conflict resolution: - flake.nix -> canonical rs-surface removal (Garnix shutdown). - scripts/math-first/* -> byte-identical across branches, clean. - .cursorrules / AGENTS.md -> unified; baselines + sorry inventory refreshed. Verification: - lake build (default aggregator): 3573 jobs, 0 errors. - lake build Semantics.RRC.PolyFactorIdentity (E8Sidon + FixedPoint + PolyFactor): 3655 jobs, 0 errors. Witnesses verified (sigma7 4 = 16513, convolutionLHS 6 = 2350). - Python tests: 68/68 pass. Note: the "Workers Builds: researchstack" check is a preexisting external Cloudflare build unrelated to this change (no branch touches 4-Infrastructure/cloudflare/). Build: 3573 jobs (default), 3655 jobs (narrow), 0 errors Co-Authored-By: Allaun Silverfox <bigdataiscoming+9i37y6j2@protonmail.com>
83 lines
3 KiB
Python
83 lines
3 KiB
Python
#!/usr/bin/env python3
|
|
# ==============================================================================
|
|
# COPYRIGHT NO ONE EVERYWHERE LLC (WYOMING HOLDING COMPANY)
|
|
# PROJECT: SOVEREIGN STACK
|
|
# This artifact is entirely proprietary and cryptographically proven.
|
|
# Open-Source usage requires explicit permission from Brandon Scott Schneider.
|
|
# ==============================================================================
|
|
import argparse
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Any, Dict, List
|
|
|
|
from jsonschema import validate
|
|
|
|
import sys
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[3] / "4-Infrastructure"))
|
|
from lib.jsonl import load_jsonl
|
|
|
|
|
|
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
|
PRE_SCHEMA = PROJECT_ROOT / "schemas" / "pre_record.schema.json"
|
|
POST_SCHEMA = PROJECT_ROOT / "schemas" / "post_record.schema.json"
|
|
def load_schema(path: Path) -> Dict[str, Any]:
|
|
return json.loads(path.read_text(encoding="utf-8"))
|
|
|
|
|
|
def parse_args() -> argparse.Namespace:
|
|
parser = argparse.ArgumentParser(description="Verify PRE/POST record schema validity and one-to-one pairing.")
|
|
parser.add_argument("--pre", required=True, help="Path to pre_records.jsonl")
|
|
parser.add_argument("--post", required=True, help="Path to post_records.jsonl")
|
|
parser.add_argument("--out", help="Optional output JSON report path")
|
|
return parser.parse_args()
|
|
|
|
|
|
def main() -> int:
|
|
args = parse_args()
|
|
pre_rows = load_jsonl(Path(args.pre))
|
|
post_rows = load_jsonl(Path(args.post))
|
|
|
|
pre_schema = load_schema(PRE_SCHEMA)
|
|
post_schema = load_schema(POST_SCHEMA)
|
|
|
|
for row in pre_rows:
|
|
validate(instance=row, schema=pre_schema)
|
|
for row in post_rows:
|
|
validate(instance=row, schema=post_schema)
|
|
|
|
pre_ids = [str(r["pre_record_id"]) for r in pre_rows]
|
|
post_pre_ids = [str(r["pre_record_id"]) for r in post_rows]
|
|
|
|
pre_set = set(pre_ids)
|
|
post_ref_set = set(post_pre_ids)
|
|
|
|
missing_post_for_pre = sorted(pre_set - post_ref_set)
|
|
orphan_post_refs = sorted(post_ref_set - pre_set)
|
|
|
|
duplicate_pre = sorted([x for x in pre_set if pre_ids.count(x) > 1])
|
|
duplicate_post_ref = sorted([x for x in post_ref_set if post_pre_ids.count(x) > 1])
|
|
|
|
ok = not (missing_post_for_pre or orphan_post_refs or duplicate_pre or duplicate_post_ref)
|
|
|
|
report: Dict[str, Any] = {
|
|
"ok": ok,
|
|
"pre_count": len(pre_rows),
|
|
"post_count": len(post_rows),
|
|
"missing_post_for_pre": missing_post_for_pre,
|
|
"orphan_post_refs": orphan_post_refs,
|
|
"duplicate_pre_record_ids": duplicate_pre,
|
|
"duplicate_post_pre_refs": duplicate_post_ref,
|
|
"pairing_ratio": (len(post_rows) / len(pre_rows)) if pre_rows else 0,
|
|
}
|
|
|
|
if args.out:
|
|
out_path = Path(args.out)
|
|
out_path.parent.mkdir(parents=True, exist_ok=True)
|
|
out_path.write_text(json.dumps(report, indent=2) + "\n", encoding="utf-8")
|
|
|
|
print(json.dumps(report, indent=2))
|
|
return 0 if ok else 2
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|