Research-Stack/shared-data
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
..
artifacts Expand devcontainer with full Python stack, add MCP servers (Notion/AWS), strengthen Lean theorems 2026-05-19 01:52:14 -05:00
data feat: eigensolid convergence proof + QC flagging tool + full pass/fail review 2026-05-14 00:04:08 -05:00
examples Add adversarial duals 16D anchor pack 2026-05-17 15:47:38 -05:00
proof_traces feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 2026-05-26 02:37:22 -05:00
schemas Add adversarial duals receipt schema 2026-05-17 15:11:34 -05:00
pist_canary_receipts.jsonl feat(pist): canary batch — 42 real Lean theorems through full pipeline 2026-05-26 02:09:08 -05:00
pist_canary_report.json feat(pist): canary batch — 42 real Lean theorems through full pipeline 2026-05-26 02:09:08 -05:00
pist_canary_results.jsonl feat(pist): canary batch — 42 real Lean theorems through full pipeline 2026-05-26 02:09:08 -05:00
pist_flexure_library_report.json feat(pist): flexure joint library in ene.flexures — 38 joints, 10 motifs 2026-05-26 10:49:49 -05:00
pist_route_repair_benchmark.json feat(pist): Route-Repair Loop v1 — 11% recovery rate 2026-05-26 11:38:01 -05:00
pist_route_repair_v11_benchmark.json feat(pist): Route-Repair v1.1 — 60 failure flexures ingested, obstruction-type voting 2026-05-26 12:17:42 -05:00
pist_route_repair_v12_benchmark.json feat(pist): Route-Repair v1.2 — 36% recovery from 0% 2026-05-26 12:38:17 -05:00
pist_route_repair_v13b_benchmark.json feat(pist): Route-Repair v1.3b — multi-step templates, 54% recovery 2026-05-26 12:56:24 -05:00
pist_route_repair_v14_benchmark.json feat(pist): Route-Repair v1.4a — 97% recovery, residual closure 2026-05-26 13:51:05 -05:00
pist_tier1_vs_tier2_comparison.json feat(pist): Tier 2 beats Tier 1 on 5/6 independent targets 2026-05-26 09:57:10 -05:00
pist_tier2b_confusion_matrices.json feat(pist): Tier 2 beats Tier 1 on 5/6 independent targets 2026-05-26 09:57:10 -05:00
pist_trace_canary_report.json feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 2026-05-26 02:37:22 -05:00
pist_trace_canary_vectors.jsonl feat(pist): Tier 2 trace canary — 24 multi-tactic Lean theorems 2026-05-26 02:37:22 -05:00
pist_trace_routing_benchmark.json feat(pist): routing benchmark — 30% tactic family prediction vs 20% baseline 2026-05-26 11:28:05 -05:00
pist_trace_scaled_report.json feat(pist): scaled Tier 2B batch — 21/64 theorems, RRCShape 71.4% 2026-05-26 10:34:32 -05:00
pist_trace_scaled_vectors.jsonl feat(pist): 57/64 theorem batch — 89.5% proof status LOOCV 2026-05-26 11:20:17 -05:00
pist_trace_tier2b_report.json feat(pist): Tier 2B spectral decomposition — first real proof-path spectra 2026-05-26 03:08:05 -05:00
pist_trace_tier2b_vectors.jsonl feat(pist): Tier 2B spectral decomposition — first real proof-path spectra 2026-05-26 03:08:05 -05:00
pist_trace_v2_canary_report.json feat(pist): Tier 2B — instrumented trace bridge with real transition matrices 2026-05-26 02:56:46 -05:00
pist_trace_v2_ground_truth_labels.jsonl feat(pist): Tier 2 beats Tier 1 on 5/6 independent targets 2026-05-26 09:57:10 -05:00
rrc_pist_exact_validation.json feat(pist): receipt canonicalization v2 with structural math features 2026-05-26 01:55:09 -05:00
rrc_pist_feature_vectors.jsonl feat(pist): receipt canonicalization v2 with structural math features 2026-05-26 01:55:09 -05:00
rrc_pist_training_report.json feat(pist): receipt canonicalization v2 with structural math features 2026-05-26 01:55:09 -05:00