allaun/Research-Stack
1
0
Fork 0
mirror of https://github.com/allaunthefox/Research-Stack.git synced 2026-07-31 03:05:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
353 commits 18 branches 0 tags 425 MiB
Commit graph

63 commits

Author SHA1 Message Date
Brandon Schneider
2400c4b731 feat(pist): scaled Tier 2B batch — 21/64 theorems, RRCShape 71.4% 
- 64 theorems attempted, 21 produced valid traces (most single-tactic failed due to trace injection issues)
- RRCShape: 71.4% LOOCV (baseline 24%) — ★ 3x baseline, consistent with v2 batch (66.7%)
- Proof method: 42.9% LOOCV (baseline 24%) — ★ beats baseline
- Domain: 14.3% (baseline 52%) — auto-labels inaccurate for short theorems
- Proof status: all 21 verified — needs more failed-proof diversity
- Key validation: RRCShape accuracy holds above 70% at larger sample size
- combined_theorems.py: 66 unique theorems across both batches
 2026-05-26 10:34:32 -05:00
Brandon Schneider
38fabb20ec feat(pist): Tier 2 beats Tier 1 on 5/6 independent targets 
Key results (Tier 2 vs Tier 1 vs baseline):
- Proof status: 83.3% vs N/A vs 50.0% — ★ strong signal
- Domain: 62.5% vs 30.9% vs 33.3% — ★ BEATS both
- Manual RRCShape: 66.7% vs 38.1% vs 29.2% — ★ BEATS both
- Obstruction: 75.0% vs N/A vs 79.2% — ↑ near-baseline
- Proof method: 20.8% vs 9.5% vs 20.8% — ↑ BEATS T1, ties baseline
- Joint: 0.0% vs N/A vs 4.2% — needs more samples (24 unique)

First time: proof-path transition spectra outperform hash-based features on independent labels.
 2026-05-26 09:57:10 -05:00
Brandon Schneider
42b4ffbf69 feat(pist): Tier 2 beats Tier 1 on every independent target 
- Domain: 62.5% vs 19.1% (baseline 33.3%) — BEATS both
- RRCShape: 66.7% vs 38.1% (baseline 29.2%) — BEATS both
- Proof method: 20.8% vs 9.5% (baseline 20.8%) — BEATS T1
- Proof status: 70.8% — useful signal
- 8/8 targets: Tier 2 outperforms Tier 1
- First proof-path spectra that beat hash-based features
 2026-05-26 03:10:22 -05:00
Brandon Schneider
7dd8dfd249 feat(pist): Tier 2B spectral decomposition — first real proof-path spectra 
- 24 transition matrices decomposed via power iteration
- Verified proofs: rank=4.00 vs Failed: rank=1.25
- Verified density 0.170 vs Failed 0.105
- 7 unique spectral gaps, 7 unique Laplacian zero counts
- Features from proof-state transitions, not receipt hashes
 2026-05-26 03:08:05 -05:00
Brandon Schneider
ea2b4dad40 feat(pist): Tier 2B — instrumented trace bridge with real transition matrices 
- 24/24 theorems produce trace tags
- 18/24 have >1x1 transition matrices (was 0 in Tier 2A)
- Unique states: avg 3.6, max 8
- Verified proofs: 5.1 avg steps vs Failed: 2.1 avg steps
 2026-05-26 02:56:46 -05:00
Brandon Schneider
153a8da5c5 feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 
- 24/24 processed, 0 errors (12 verified, 12 failed)
- Average 2.0 steps per proof (max 5 steps)
- 11 tactic families detected
- Verified proofs: avg gap=2.50 vs Failed: avg gap=1.50
- proof_traces/*.trace.json + *.decomp.json stored per theorem
 2026-05-26 02:37:22 -05:00
Brandon Schneider
bef48acee4 feat(pist): canary batch — 42 real Lean theorems through full pipeline 
- 42/42 unique matrix hashes (100%)
- 42/42 unique canonical hashes (no collisions)
- 42/42 unique spectral gaps (full diversity)
- Rank estimate: 5 distinct values, range [4, 8]
- Laplacian zero count: 3 distinct values, range [1, 3]
- 1 outlier: omega_double classified as CadForceProbeReceipt (rank=4)
- Classifier still collapses to LogogramProjection for rank>=5

Conclusion: spectral features are diverse. Classifier thresholds need training, not hand-tuning.
 2026-05-26 02:09:08 -05:00
Brandon Schneider
6c55cac0a9 feat(pist): receipt canonicalization v2 with structural math features 
- Parses equation names into operators, variables, AST metrics, proof metrics
- Richer canonical hash → more distinct crossing matrices
- Separation ratio improved: 1.007 → 1.051 (within/between class distance)
- CognitiveLoadField accuracy: 44.4% → 50.0%
- Fold/cusp confusion (CLF → SRC): 9/18 → 3/18 (major improvement)
- 26/26 unique matrix hashes maintained
- Receipt format: v1 → v2 (parse_equation + build_proof_metrics)
 2026-05-26 01:55:09 -05:00
Brandon Schneider
c7eed520f9 feat(pist): validation + calibration harness 
- pist_train.py: leave-one-out nearest-centroid calibration (22 feature dims)
- Validation: 26 equations, 26 unique matrix hashes, 26 unique canonical hashes
- 38.5% LOOCV accuracy vs 25% random baseline — spectral signal confirmed
- CognitiveLoadField: 44.4% (8/18), SignalShapedRouteCompiler: 33.3% (2/6)
- Separation ratio 1.007 — centroids overlap heavily (fold/cusp are adjacent in ADE)
- Feature diversity confirmed: 21/22 features carry variance
 2026-05-26 01:49:21 -05:00
Brandon Schneider
96be7cdb97 feat(pist): exact eigendecomposition, matrix diagnostics, 26-equation validation 
- pist-decompose: convergence proxy + symmetric/Laplacian/SVD spectrum
- Crossing matrix now hash-derived (Q0_2), unique per equation
- Validation: 26/26 unique matrices, 26/26 unique canonical hashes
- Spectral features: rank(5), density(10), entropy(26), gap(26)
- Classifier rules need labeled training data
- pist_classify.py: full pipeline wrapper
- validate_rrc_predictions.py: batch runner with diagnostics
 2026-05-26 01:20:30 -05:00
Brandon Schneider
fd863af6fd Expand devcontainer with full Python stack, add MCP servers (Notion/AWS), strengthen Lean theorems 
- .devcontainer/Dockerfile: add PostgreSQL client libs, OpenSSL/libffi headers, gfortran/BLAS for scipy, rclone; install full Python dependency set (boto3, psycopg2-binary, fastapi, uvicorn, notion-client, httpx, pytest, numpy, scipy, etc.) in uv-managed venv; add rclone S3 gateway init script as ENTRYPOINT
- .devcontainer/devcontainer.json: switch from build to pre-built image (localhost/research
 2026-05-19 01:52:14 -05:00
Allaun Silverfox
60fd8fbc05 Add adversarial duals 16D anchor pack 2026-05-17 15:47:38 -05:00
Allaun Silverfox
80389d3d3d Add adversarial duals example config 2026-05-17 15:45:57 -05:00
Allaun Silverfox
b553570c94 Add adversarial duals receipt schema 2026-05-17 15:11:34 -05:00
Allaun Silverfox
518f3d96ce Add Plasma Chiral Drag Witness example config 2026-05-17 10:14:06 -05:00
Allaun Silverfox
002e956e34 Add Plasma Chiral Drag Witness receipt schema 2026-05-17 10:12:58 -05:00
Allaun Silverfox
5527a00b8d Add BraidStorm Sidon Crossing 16D anchor pack 2026-05-16 20:57:35 -05:00
Allaun Silverfox
f692239078 Add BraidStorm Sidon Crossing example config 2026-05-16 20:56:35 -05:00
Allaun Silverfox
5f051465d2 Add BraidStorm Sidon Crossing receipt schema 2026-05-16 20:56:00 -05:00
Allaun Silverfox
0c4055d054 Add Golden Braid Centering 16D anchor pack 2026-05-16 20:25:22 -05:00
Allaun Silverfox
bdde1f873c Add Golden Braid Centering example config 2026-05-16 20:24:20 -05:00
Allaun Silverfox
4163d1e2ac Add Golden Braid Centering receipt schema 2026-05-16 20:20:42 -05:00
Allaun Silverfox
de689b58d3 Add autonomous speedrun 16D anchor pack 2026-05-16 19:16:02 -05:00
Allaun Silverfox
764354f83d Add autonomous speedrun harness example 2026-05-16 19:12:25 -05:00
Allaun Silverfox
f76816548f Add autonomous speedrun harness receipt schema 2026-05-16 19:10:51 -05:00
Allaun Silverfox
0ff6cc60fd Add MarkovJunior 16D shim example config 2026-05-16 18:47:53 -05:00
Allaun Silverfox
92fdd77593 Add MarkovJunior 16D shim receipt schema 2026-05-16 18:45:37 -05:00
Allaun Silverfox
15a03119ae Add Sidon 16D anchor pack 2026-05-16 17:21:03 -05:00
Allaun Silverfox
3f28a32db8 Add Sidon FAMM map example config 2026-05-16 17:20:33 -05:00
Allaun Silverfox
9cd2729fbc Add Sidon FAMM map receipt schema 2026-05-16 17:19:43 -05:00
Allaun Silverfox
a49292418f Add Builder-Judge-Warden Erdos-Szekeres example 2026-05-16 17:06:26 -05:00
Allaun Silverfox
d0999cf1d3 Add Builder-Judge-Warden cleanup receipt schema 2026-05-16 17:00:28 -05:00
Allaun Silverfox
3016c13c72 Add 16D logogram chirality anchor pack 2026-05-16 16:36:53 -05:00
Allaun Silverfox
514a23cbb6 Add logogram chirality witness example 2026-05-16 16:35:55 -05:00
Allaun Silverfox
aec95d2a82 Add logogram chirality witness schema 2026-05-16 16:35:07 -05:00
Allaun Silverfox
6739070ad7 Add NUVMAP Delta-DAG graph coloring example 2026-05-16 16:15:20 -05:00
Allaun Silverfox
91fed078f1 Add NUVMAP Delta-DAG receipt schema 2026-05-16 16:14:43 -05:00
Allaun Silverfox
5356f8fdc2 Add common-noise MFG 16D anchor pack 2026-05-16 15:11:10 -05:00
Allaun Silverfox
c447e0373e Add bio-organoid 16D anchor pack 2026-05-16 14:54:17 -05:00
Allaun Silverfox
e372679c45 Add 16D Chaos Game example config 2026-05-16 14:44:29 -05:00
Allaun Silverfox
cbfe556315 Add 16D Chaos Game receipt schema 2026-05-16 14:43:21 -05:00
Allaun Silverfox
1296c165f0 Add example Semantic Mass route plow config 2026-05-16 13:50:19 -05:00
Allaun Silverfox
d6859ecd23 Add Semantic Mass route plow receipt schema 2026-05-16 13:42:25 -05:00
Allaun Silverfox
f56d90fb9d Add example Semantic Mass Z accelerator config 2026-05-16 13:27:42 -05:00
Allaun Silverfox
f7283be9c1 Add Semantic Mass Z receipt schema 2026-05-16 13:25:39 -05:00
Allaun Silverfox
b2f16b8114 Add example FAMM Hessian receipt config 2026-05-16 13:17:24 -05:00
Allaun Silverfox
f0c26fccd1 Add FAMM Hessian curvature receipt schema 2026-05-16 13:16:48 -05:00
Brandon Schneider
7a20002fc2 feat: eigensolid convergence proof + QC flagging tool + full pass/fail review 
Resolves the convergence_to_fixed_point failure by proving the correct
eigensolid statement: stepExact stabilizes all value components (N_7,
N_8, N_11) in one application. The original theorem was mathematically
false (iteration counter is free-running).

QC cleanup sweep across Physics/ (20 files):
- 3 remaining LOW items fixed: h00/h01 factoring, rD->rd, rdDr1/rdDr2 x100
- 6 of 7 sorry theorems proved; 1 explicitly FAILED (convergence)
- Unused imports removed, naming violations fixed, #eval witnesses added
- 210 -> 144 issues remaining (all WARNING/INFO, zero ERROR)

New tooling:
- scripts/qc-flag/lean_qc_flagger.py implemements 5-point inspection protocol
- Outputs structured JSON + Markdown pass/fail reports

DAG receipts at shared-data/data/stack_solidification/qc_*_dag_2026-05-13.md
 2026-05-14 00:04:08 -05:00
Brandon Schneider
302f48d416 chore: QC report — 14 structural/efficiency issues found 
HIGH (4): absDiff 4x duplicated, scale 6x duplicated,
         duplicate theorems, dead q16_div
MEDIUM (5): dead DESIParam, q16Abs=Int.abs, dead structures,
           25 theorems unconsolidated, q16_div duplicated
LOW (5): Hermite helper, Q16.16 consistency, SCALE casing,
         rD field naming, rd precision
 2026-05-13 22:11:16 -05:00
Brandon Schneider
aa4563cdf5 feat: create Lean Expert Agent with full inspection protocol 
Agent inspects Lean code for:
1. Structural health (theorem/def/eval/sorry counts)
2. Naming conventions (camelCase/PascalCase per AGENTS.md)
3. Q0_16/Q16_16 compliance
4. Proof quality (native_decide, .isSome guards, tautologies)
5. Dependency analysis (unused imports, circular deps)

First inspection of Physics/ found 95 issues:
  79 naming violations (systematic snake_case)
  2 unused imports (Semantics.FixedPoint)
  4 trivial/tautological proofs
  3 #eval vs #eval! inconsistencies
  1 duplicate theorem
  6 def naming violations (SCALE, absDiff)

Trigger with: /inspect <target>
 2026-05-13 22:01:12 -05:00