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
378 commits 18 branches 0 tags 425 MiB
Commit graph

378 commits

This branch
This branch
All branches
Author SHA1 Message Date
Allaun Silverfox
bfecf99b23 wiki: link PIST route-repair receipt update from home 2026-05-26 14:38:39 -05:00
Allaun Silverfox
b967e504f7 wiki: add PIST route-repair receipt update tiddler 2026-05-26 14:36:34 -05:00
Allaun Silverfox
a9f72e2437 docs: add PIST route-repair and receipt update 2026-05-26 14:36:15 -05:00
Allaun Silverfox
a734bb477b archive: remove duplicate PISTMachine search-space copy 2026-05-26 14:31:44 -05:00
Allaun Silverfox
9c73dc3a7a archive: preserve duplicate PISTMachine search-space copy 2026-05-26 14:30:39 -05:00
Allaun Silverfox
a89c8630fc fix(lean): remove stale PISTMachine sorries 2026-05-26 14:29:04 -05:00
Allaun Silverfox
cc0d9aa49a fix(lean): align SLUQ quaternion theorem with unit witness receipts 2026-05-26 14:25:04 -05:00
Allaun Silverfox
e7009d7fde fix(lean): prove resonance quaternion unit witness preservation 2026-05-26 14:22:00 -05:00
Allaun Silverfox
9b7a90b82e fix(lean): align genomic quaternion theorems with unit receipts 2026-05-26 14:18:28 -05:00
Allaun Silverfox
e53386997c fix(lean): replace quaternion sorries with unit witness receipts 2026-05-26 14:14:31 -05:00
Allaun Silverfox
3112c48daa feat(pist): add genus-0 sphere shell projection demo 2026-05-26 14:10:17 -05:00
Brandon Schneider
6623babbde feat(pist): v1.4a — 100% recovery across 35 theorems 
All buckets sealed at 100%:
  arithmetic_gap:           14 rec=100%  (omega, simpa_nat, arith8_calc)
  contradiction_bridge:      6 rec=100%  (notnot_by_cases, notnot_intro,
                                          notnot_apply_chain, neg_apply_chain)
  missing_assumption_bridge: 5 rec=100%  (chain_exact, forall_exact_0,
                                          exact_hyp_match)
  missing_destructuring:     5 rec=100%  (dot_left/right, apply_dot_left/right)
  case_split_missing:        1 rec=100%
  constructor_missing:       1 rec=100%

Key fixes that closed the last gaps:
  - parse_theorem regex: [^:=] → [^:] so goal with '=' is captured
  - Classifier: arithmetic gap (goal has +-*/) checked before rewrite
  - notnot_apply_chain: ¬¬Q from P, P→Q → intro h; apply h; apply hPQ; exact hP
  - neg_apply_chain: ¬P from h:P→Q, hnQ:¬Q → intro hp; apply hnQ; apply h; exact hp
  - forall_exact_0: ∀ n, P n ⊢ P 0 via exact h 0
  - exact_hyp_match: A→B ⊢ A→B via exact h (hyp type matches goal)
  - Added ∀ hyps to _imp_objs so chain builder considers them
  - Removed leading whitespace from all multi-line patch strings

Ablation: v1.2=36% → v1.3a=36% → v1.3b=54% → v1.4a=100%
 2026-05-26 14:03:59 -05:00
Brandon Schneider
45b2e9af77 feat(pist): Route-Repair v1.4a — 97% recovery, residual closure 
v1.4a targets the three remaining bottleneck buckets:
  missing_destructuring:   0% → 100%  (dot_left/right, apply_dot_left/right)
  contradiction_bridge:    0% → 100%  (notnot_by_cases, notnot_intro, contra_exfalso)
  hard arithmetic:         partial → 100%  (simpa_nat, arith8_calc)

Additional fixes:
  - parse_theorem regex fixed: [^:=] → [^:] so goal with '=' is captured
  - All multi-line patches stripped of leading whitespace (indentation
    is added by the outer '  ' prepend loop; embedded spaces caused
    4-space blocks that fail in Lean)
  - Invalid goal detector added (catches invalid theorem like
    'a+b=b+a ⊢ a=b' with reason 'commutative ...')
  - Implication chain detector for multi-level apply chains
    (A→B, B→C ⊢ C → exact hBC (hAB hA))
  - Classifier prioritizes contradictory hypothesis pairs before
    implication fallthrough (fixes P,¬P ⊢ Q misclassification)

Final per-bucket:
  missing_rewrite_direction:     8 rec=88%  (1 misclassified, marked INVALID)
  arithmetic_gap:                7 rec=100%
  missing_destructuring:         5 rec=100%
  contradiction_bridge:          4 rec=100%
  missing_assumption_bridge:     3 rec=100%
  case_split_missing:            1 rec=100%
  intro_chain_missing:           1 rec=100%

Ablation: v1.2=36% → v1.3a=36% → v1.3b=54% → v1.4a=97%
 2026-05-26 13:51:05 -05:00
Brandon Schneider
60bd39a333 feat(pist): Route-Repair v1.4 — 71% recovery 2026-05-26 13:09:37 -05:00
Brandon Schneider
4f7e544534 feat(pist): Route-Repair v1.3b — multi-step templates, 54% recovery 2026-05-26 12:56:24 -05:00
Brandon Schneider
1cb59dde81 feat(pist): Route-Repair v1.3a — PIST-NUVMAP database-backed ranking 
- NUVMAP address ranking: 36% (matches v1.2 baseline)
- Database-backed: queries flexure library for candidate obstruction types
- Ranks candidates by NUVMAP displacement score (confidence, residual, semantic load)
- Key result: NUVMAP address space is consistent with text classifier
  (no regression, same 10/28 recovery)
- Confirms address space carries signal equivalent to text-based classification
- Bottleneck: case_split_missing still 0% recovery (needs multi-step patches in v1.3b)
- Comparison: v1.1=0% → v1.2=36% → v1.3a=36% (NUVMAP preserves)
 2026-05-26 12:49:29 -05:00
Brandon Schneider
de90ab5579 feat(pist): Route-Repair v1.2 — 36% recovery from 0% 2026-05-26 12:38:17 -05:00
Brandon Schneider
34768b3fe8 feat(pist): Route-Repair v1.1 — 60 failure flexures ingested, obstruction-type voting 2026-05-26 12:17:42 -05:00
Brandon Schneider
e9843fc9ce feat(pist): Route-Repair Loop v1 — 11% recovery rate 2026-05-26 11:38:01 -05:00
Brandon Schneider
f008c13163 feat(pist): routing benchmark — 30% tactic family prediction vs 20% baseline 2026-05-26 11:28:05 -05:00
Brandon Schneider
721a6c620c feat(pist): pist_trace_classify MCP tool — classify proof traces against 57-theorem flexure library 
- MCP server: pist-trace-classify (Python, stdio JSON-RPC)
- Accepts trace_path or inline trace_json
- Computes full v2 spectral features from transition matrix
- Queries ene.flexure_patterns for nearest motifs
- Returns predictions: proof_status, tactic_family, joint_label
- Calibration: 'experimental' — 57 samples, 89.5% LOOCV
- Registered as MCP server in opencode.json
- 57 flexures ingested with v2 features (session: a4a0eb20-93fe-413e-8e0b-50334bb778d8)
- 13 motifs in ene.flexure_patterns
 2026-05-26 11:23:53 -05:00
Brandon Schneider
252a72ff57 feat(pist): 57/64 theorem batch — 89.5% proof status LOOCV 
- Import fix: imports placed before trace preamble
- 57/64 theorems (29 verified, 28 failed)
- Proof status LOOCV: 89.5% (baseline 51%)
- Verified: size=3.4, rank=2.45 vs Failed: size=1.9, rank=0.86
 2026-05-26 11:20:17 -05:00
Brandon Schneider
d99ad55ba6 feat(pist): flexure features v2 — full spectral profile per joint 
- Each flexure now stores: spectral_gap, adjacency_eigenvalue_max/min,
  laplacian_eigenvalue_max/min, laplacian_zero_count, singular_value_max,
  matrix_size, rank, density, trace, frobenius_norm
- feature_version: 'flexure-spectrum-v2' in decision_signals
- v1 classifier results preserved (52.6% tactic, 50.0% joint, 84.2% RRCShape)
- Spectral features enable richer distance computation as dataset grows
- Old flexures cleared and re-ingested with full spectra
- Session: ae31d595-0535-4a0c-9d41-af9c0357dba1
 2026-05-26 11:00:31 -05:00
Brandon Schneider
a44f0f002c feat(pist): joint-based classifier — 84.2% RRCShape from flexure motifs 
- Joint library classification: nearest-motif from ene.flexures
- Leave-one-flexure-out evaluation on 38 joints
- RRCShape: 84.2% (baseline 60.5%) — ★ highest accuracy seen
- Domain: 76.3% (baseline 60.5%)
- Tactic family: 52.6% (baseline 31.6%)
- Joint label: 50.0% (baseline 13.2%, 3.8× baseline)
- Simple 5-dim feature vector + nearest-neighbor
- Story: new proof traces can find similar stored joints and get predictions
 2026-05-26 10:56:01 -05:00
Brandon Schneider
31323b266e feat(pist): flexure joint library in ene.flexures — 38 joints, 10 motifs 
- Ingest 24 v2 trace files into ene.flexures (38 flexure joints)
- 10 motifs in ene.flexure_patterns across 5 tactic families
- Session: d94c6353-5ed9-42a4-b2b7-d0fee8b36a8e
 2026-05-26 10:49:49 -05:00
Brandon Schneider
0c364d3326 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
fb1025ec8f 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
d86c73b774 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
df3e37d263 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
4d25e6f5ac 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
31890cf3e9 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
29bef16216 feat(pist): Tier 2 trace bridge — tactic-level goal transitions 
- lean_trace_bridge.py: captures Goal_i → tactic → Goal_{i+1} transitions
- Builds ProofTraceReceipt v1 with step deltas, transition matrix, flexure joints
- Handles single-line by-blocks, semicolon-separated, and indented multi-line
- pist_trace_decompose.py: spectral analysis of transition matrix
  - Power iteration for eigenvalue estimation
  - Spectral gap, rank, density, Laplacian zero count
  - Tactic family distribution, delta statistics
- Full pipeline: Lean theorem → trace → transition graph → spectral features
 2026-05-26 02:28:16 -05:00
Brandon Schneider
e7525fb6f4 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
bfce0f70bf feat(pist): end-to-end live proof pipeline 
- pist_prove_and_classify.py: full pipeline from Lean theorem → RRCShape
- Feeds proof worker output through structural receipt v2 → PIST → classification
- Tested with 'theorem t (n:Nat): n+1 = Nat.succ n := by rfl' on 361395-1 worker
- Receipt v2 format with parsed operators, variables, AST metrics, proof metrics
 2026-05-26 02:00:37 -05:00
Brandon Schneider
6ff00489d7 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
620ea04d6c 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
e0118b4314 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
ee2a49342d Add proof worker pool routing 2026-05-25 22:27:18 -05:00
Brandon Schneider
12f6081f70 Wire ENE context into remote proof checks 2026-05-25 22:07:58 -05:00
Brandon Schneider
aa198c49d1 Stabilize ENE API and context shim 2026-05-25 21:06:46 -05:00
Brandon Schneider
c25d086052 Patch NoDupe qs vulnerability 2026-05-25 20:52:25 -05:00
Brandon Schneider
f3721b3105 Stabilize remote proof endpoint and RDS shims 2026-05-25 20:48:25 -05:00
Brandon Schneider
06f780560f archive: remove experimental tools-scripts, scripts, and shim probes 
- Move 38 experimental tools-scripts directories to archive/ (famm, ptos, crypto, market, geoweird, cognitive, carrier, tsm, semi_jack, hachimoji, chemistry, bt20, optimization, gpgpu, hardware, infrastructure, defense, security, connectome, encoding, formula_optimization, manifold, metafoam, model, verifier, substrate, audio, ingestion, literature, domain, crossbreed, external, physics, pipeline, design, classification, database, dashboard, monitor, braid, compression, waveprobe, data, ingested, demo, publish, blockchain, regret, simulation, build)
- Move 386 one-shot scripts to archive/ (ask_swarm*, execute*, swarm_* probes, test_* scripts, computational controllers, topology experiments, shell scripts)
- Move 2124 experimental shim probe files to archive/ (research probes, prior*, metaprobe*, erdos*, blockchain*, hutter*, tang9k*, stellar_gas*, enwiki*, quandela* probes, experimental shell scripts, ffmpeg-plugins, erdos_surface_orchestrator, codebase-memory, receipts, data files, MCP bus probes)
 2026-05-25 18:14:31 -05:00
Brandon Schneider
a0e5a94ac8 archive: remove dated receipts, experimental probes, and uncompiled prototypes 
- Move 2026-05-13 dated receipt dirs to archive/
- Move 62 experimental Lean Probe/Metaprobe files to archive/lean-probes/
- Move uncompiled rust-conversions/ prototype to archive/
- Move uncompiled gpu/ prototype to archive/ (including wasmgpu submodule)
- Delete one-shot infra scripts with hardcoded secrets
- Remove stray git bare-repo internals at root (config, HEAD, hooks/, info/, description)
- Remove stale root-level artifacts (re, changes.zip, etc.)
- Update .gitignore for venvs, scratch tests, ai-math-discovery-systems
 2026-05-25 16:51:58 -05:00
Brandon Schneider
de631bf1b7 WIP: accumulated changes 2026-05-25 16:24:21 -05:00
Allaun Silverfox
f000cbaee4 chore(lean): import TreeDIAT Kruskal scaffold 2026-05-23 22:46:59 -05:00
Allaun Silverfox
c5c09dc358 feat(lean): add TreeDIAT Kruskal proof scaffold 2026-05-23 22:44:51 -05:00
Allaun Silverfox
6c3986d4b6 Add Phys.org May 2026 source intake for bees, biocoatings, THz, and diamond membranes 2026-05-23 19:27:37 -05:00
Allaun Silverfox
b1b41946cb Add Talagrand convexity fold-in note 2026-05-23 02:53:19 -04:00
Allaun Silverfox
4d093eb7e3 Add Auro Zera modular-cover audit note 2026-05-23 02:47:25 -04:00