Research-Stack/4-Infrastructure/shim
Brandon Schneider d6f4df42b5 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
..
authentik_agent_manager WIP: accumulated changes 2026-05-25 16:24:21 -05:00
lake_compile_bridge style(compile-bridge): format GPU verifier 2026-05-20 18:46:49 -05:00
netwatch WIP: accumulated changes 2026-05-25 16:24:21 -05:00
tang9k_ipc_worker WIP: accumulated changes 2026-05-25 16:24:21 -05:00
batch_embed_artifacts.py Stabilize remote proof endpoint and RDS shims 2026-05-25 20:48:25 -05:00
beaver_mask_freshness_negative_controls.py Stage stack solidification source slice 2026-05-11 22:08:10 -05:00
combined_theorems.py feat(pist): scaled Tier 2B batch — 21/64 theorems, RRCShape 71.4% 2026-05-26 10:34:32 -05:00
compare_tier1_vs_tier2.py feat(pist): Tier 2 beats Tier 1 on 5/6 independent targets 2026-05-26 09:57:10 -05:00
credential_loader.py WIP: accumulated changes 2026-05-25 16:24:21 -05:00
dataset_ingest_rds.py Expand devcontainer with full Python stack, add MCP servers (Notion/AWS), strengthen Lean theorems 2026-05-19 01:52:14 -05:00
decompose_tier2b_traces.py feat(pist): Tier 2B spectral decomposition — first real proof-path spectra 2026-05-26 03:08:05 -05:00
ene_migrate_and_tag.py Expand devcontainer with full Python stack, add MCP servers (Notion/AWS), strengthen Lean theorems 2026-05-19 01:52:14 -05:00
ene_substrate_schema.sql Expand devcontainer with full Python stack, add MCP servers (Notion/AWS), strengthen Lean theorems 2026-05-19 01:52:14 -05:00
ene_wiki_body_reingest.py Quarantine sorry blocks, fix RcloneIntegration proof, add ENE wiki re-ingest and ZFS setup. 2026-05-18 23:01:44 -05:00
failure_flexure_bank.py feat(pist): Route-Repair v1.1 — 60 failure flexures ingested, obstruction-type voting 2026-05-26 12:17:42 -05:00
gpu_fpga_ipc_symbol_surface.py WIP: accumulated changes 2026-05-25 16:24:21 -05:00
hutter_jxl_starfield_eigenprobe.py Stage JXL starfield replay slice 2026-05-11 22:08:44 -05:00
hutter_jxl_starfield_replay_verify.py Stage JXL starfield replay slice 2026-05-11 22:08:44 -05:00
ingest_57_flexures.py feat(pist): pist_trace_classify MCP tool — classify proof traces against 57-theorem flexure library 2026-05-26 11:23:53 -05:00
ingest_flexure_joints.py feat(pist): flexure features v2 — full spectral profile per joint 2026-05-26 11:00:31 -05:00
joint_classifier.py feat(pist): flexure features v2 — full spectral profile per joint 2026-05-26 11:00:31 -05:00
lean_trace_bridge.py feat(pist): Tier 2 trace bridge — tactic-level goal transitions 2026-05-26 02:28:16 -05:00
lean_trace_bridge_v2.py feat(pist): 57/64 theorem batch — 89.5% proof status LOOCV 2026-05-26 11:20:17 -05:00
Modelfile.gemma-physics-math Track remaining source and documentation inventory 2026-05-11 22:18:31 -05:00
pist_canary_batch.py feat(pist): canary batch — 42 real Lean theorems through full pipeline 2026-05-26 02:09:08 -05:00
pist_classify.py feat(pist): exact eigendecomposition, matrix diagnostics, 26-equation validation 2026-05-26 01:20:30 -05:00
pist_prove_and_classify.py feat(pist): end-to-end live proof pipeline 2026-05-26 02:00:37 -05:00
pist_route_repair.py feat(pist): Route-Repair Loop v1 — 11% recovery rate 2026-05-26 11:38:01 -05:00
pist_trace_classify_mcp.py feat(pist): pist_trace_classify MCP tool — classify proof traces against 57-theorem flexure library 2026-05-26 11:23:53 -05:00
pist_trace_decompose.py feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 2026-05-26 02:37:22 -05:00
pist_train.py feat(pist): validation + calibration harness 2026-05-26 01:49:21 -05:00
route_repair_v11.py feat(pist): Route-Repair v1.1 — 60 failure flexures ingested, obstruction-type voting 2026-05-26 12:17:42 -05:00
route_repair_v12.py feat(pist): Route-Repair v1.2 — 36% recovery from 0% 2026-05-26 12:38:17 -05:00
route_repair_v13a.py feat(pist): Route-Repair v1.3a — PIST-NUVMAP database-backed ranking 2026-05-26 12:49:29 -05:00
route_repair_v13b.py feat(pist): Route-Repair v1.4a — 97% recovery, residual closure 2026-05-26 13:51:05 -05:00
route_repair_v14.py feat(pist): Route-Repair v1.4 — 71% recovery 2026-05-26 13:09:37 -05:00
route_repair_v14a.py feat(pist): Route-Repair v1.4a — 97% recovery, residual closure 2026-05-26 13:51:05 -05:00
routing_benchmark.py feat(pist): routing benchmark — 30% tactic family prediction vs 20% baseline 2026-05-26 11:28:05 -05:00
run_scaled_trace.py feat(pist): scaled Tier 2B batch — 21/64 theorems, RRCShape 71.4% 2026-05-26 10:34:32 -05:00
run_trace_canary.py feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 2026-05-26 02:37:22 -05:00
run_trace_v2_canary.py feat(pist): Tier 2B — instrumented trace bridge with real transition matrices 2026-05-26 02:56:46 -05:00
seed_flexure_dataset.py feat(pist): exact eigendecomposition, matrix diagnostics, 26-equation validation 2026-05-26 01:20:30 -05:00
stack_fail_closure_register.py Stage stack solidification source slice 2026-05-11 22:08:10 -05:00
stack_solidification_audit.py Stage stack solidification source slice 2026-05-11 22:08:10 -05:00
sync_wiki_to_rds.py Stabilize remote proof endpoint and RDS shims 2026-05-25 20:48:25 -05:00
tang9k_uart_beacon_probe.py Stage stack solidification source slice 2026-05-11 22:08:10 -05:00
trace_canary_theorems.py feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 2026-05-26 02:37:22 -05:00
validate_rrc_predictions.py feat(pist): receipt canonicalization v2 with structural math features 2026-05-26 01:55:09 -05:00