SilverSight/AGENTS.md
allaun 1a26de076d fix(lean): address vacuous rfl proofs in Chentsov theorem and close Hermite sieve proofs
- ChentsovFinite.lean: Replaced vacuous rfl proofs at uniform distribution permutation invariance, diagonal case, and off-diagonal case with explicit proof obligations and sorry.
- section2_hermite_sieve.lean: Proved repunit strict monotonicity and lower bound lemmas, closing relevant sorry placeholders.
- BindingSiteEntropy.lean: Swapped geodesicDistance placeholder with fisherRaoApprox and added counterexample sketch for fisher_implies_similar_druggability.
- FixedPoint.lean, lakefile.lean, gemma4_mcp.py: Minor fixes and enhancements.
- AGENTS.md: Tracked open Chentsov proof obligations.

Build: 2987 jobs, 0 errors (lake build)
2026-06-23 05:11:04 -05:00

5.1 KiB
Raw Blame History

AGENTS.md — SilverSight

SilverSight is the clean-slate rebase of the Research Stack.

Repository

GitHub: https://github.com/allaunthefox/SilverSight Local clone: /tmp/SilverSight (or wherever you clone it) Formal modules: formal/SilverSight/

Location (in Research Stack — for lake build integration)

0-Core-Formalism/lean/SilverSight/
  SilverSight/
    Schema.lean
    WireFormat.lean
    ProductSchema.lean
    ProductWireFormat.lean
    Receipt.lean
    Bind.lean
  SilverSight.lean          ← root import

Rules

  1. SilverSight is the ONLY target for new formal work. Do NOT add new modules to 0-Core-Formalism/lean/Semantics/Semantics/. All new Lean code goes to the SilverSight repository.

  2. Imports from Semantics are allowed (cross-project): import Semantics.FixedPoint, import Semantics.Spectrum, etc.

  3. No sorry in committed code. Same rule as the Research Stack.

  4. No Float in compute paths. Use Q0_16 or Q16_16.

  5. Build gate: lake build SilverSight must pass (3307 jobs, 0 errors as of 2026-06-22).

  6. Every new module needs:

    • @[simp] theorems for key computations
    • #eval witnesses with expected output in comments
    • A docstring explaining the module's purpose
  7. The claim manifest lives at 6-Documentation/docs/claims/manifest_v1.json (shared with Research Stack docs).

What Belongs Here

  • Schema/Layout/WireFormat core (YaFF-inspired)
  • Product-type encoders
  • Receipt/Bind composition primitive
  • DynamicCanal physics (when ported)
  • RRC corpus and PIST pipeline (when ported)
  • Compression theorems (when ported)

What Does NOT Belong Here

  • Research Stack legacy modules (stay in Semantics/Semantics/)
  • Python shims (stay in 4-Infrastructure/shim/)
  • Documentation (stay in 6-Documentation/)
  • Extraction JSONs (stay in extraction/)
ID Research Stack source SilverSight target Status
nuvmap-port Semantics.InvariantReceipt.Instances.NUVMAP formal/SilverSight/InvariantReceipt/NUVMAP.lean Not started
lambda-threshold (no RS source — new theorem) formal/SilverSight/PIST/BmcteThreshold.lean Not started
chentsov-h9 ChentsovFinite.lean:~608 same file — h9 in hc_pos ⚠️ sorry; closable via h_perm (Equiv.swap 1 2) + simp; est. ~20 lines
chentsov-diagonal ChentsovFinite.lean:~836 same file — diagonal h_agree ⚠️ sorry; needs Steps AE: h_inv at splitIdx=iIsFunctionalEquationfunctional_eq_uniquec_val/p_i; est. ~100 lines
chentsov-offdiag ChentsovFinite.lean:~862 same file — off-diagonal h_agree ⚠️ sorry; needs Steps AC: h_inv at splitIdx=0 → functional eq for cross term → c_val/p_0; est. ~80 lines

Current Status

Module Status Sorry
Schema.lean Complete 0
WireFormat.lean Complete 0
ProductSchema.lean Complete 0
ProductWireFormat.lean Complete 0
Receipt.lean Complete 0
Bind.lean Complete 0
PIST/Spectral.lean Complete 0

BMCTE Eigensolid Threshold (p/N = 1/7)

Result: λ = exp(-p²/N) → 0 at threshold confirms theoretical prediction

Implementation:

  1. NUVMAP sparse rollup (extension_v2_chunked.py) - saves state per step
  2. Spectral witness (PIST/SpectralWitness.lean) - computes spectral profile
  3. NEON spectral driver (nuvmap_spectral_driver.py) - verified 9984 gap value

Status:

  • λ(eigensolid) = 0 confirmed via formula
  • Spectral gap trivially equals input matrix diagonal values (needs parametric sweep)
  • TODO(lean-port): NUVMAP module not yet ported to SilverSight

Files:

  • experiments/bosonic_continuous/*.json — receipts
  • formal/SilverSight/PIST/SpectralWitness.lean — spectral witness
  • experiments/graph_erdos_renyi/*.py and *.png — visualization (note: 1/n ≠ 1/7 thresholds)

MCP Tools Available

Tool Module Purpose
gemma-lean-port.find_todo_sorries tools-scripts/llm/gemma_lean_port_harness.py Find TODO(lean-port) theorems
gemma-lean-port.port_theorem tools-scripts/llm/gemma_lean_port_harness.py Generate + validate Lean proofs via Gemma4-12B
loogle-search.loogle_search (planned) tools-scripts/mcp/loogle_mcp.py Search Lean/Mathlib symbols

MCP Configuration

Add to ~/.config/opencode/mcp.json:

{
  "mcpServers": {
    "gemma-lean-port": {
      "command": "python3",
      "args": ["SilverSight/5-Applications/tools-scripts/llm/gemma_lean_port_harness.py"]
    }
  }
}

Env vars:

Baker Analogue Integration

The VCN-FAMM-Sidon system is a Baker-style transcendental framework where:

  • Sidon addresses = injectivity constraints
  • Collapse functional Λ = ∑ wᵢⱼₖₗ log(aᵢ + aⱼ)
  • Scar energy Ω = ∑ scar.pressure
  • Theorem: |Λ| ≥ ε(X) Ω > 0 (rigidity OR scar emission)