- Mathlib Module Verification v0.2 project execution hardening: implemented/in progress.
Existential Agent Ecology
-> API / SDK / CLI
-> Domain Claim
-> Semantic / Natural-Language Intake
-> Formal-World Adapter Registry
-> Adapter Capability / Parse / Normalize / Validate
-> Proof-System Project Registry
-> Artifact Manifests / Import Graphs / Check Requests
-> Continuation Actions
-> Continuation Curriculum
-> Verification Episode
-> Verifier / Importer / Finite Validator / Chain Audit
-> Proof Digestion
-> Verifier Feedback / Repair
-> Discovery Value
-> Lawbook Acceptance
-> Lawbook Query / Known Skip
-> Structural Identity
-> Habit Rules
-> Reason Compression
-> Process Memory
-> Structure Registry / Typed Projection
-> Role-Based Object Introduction
-> Structural Analogy / Exposition
-> Projection
-> Telemetry
- M0 Closed-Loop Certificate Smoke
- M1 Agentic Alchemical Loop
- M2 Projection Engine
- M3 Root-Aware Constructors
- M4 TRUE-Side Proof Verification
- M4.5 Unified Verification Episode
- M5 Route Telemetry and Spectral H-Tilt
- M6 Domain-General Claim IR
- M6.5 Lean Adapter Hardening
- M6.6 Continuation Actions
- M6.7 Proof Digestion
- M6.8 Verifier Feedback / Repair
- M6.8.1 Verifier Feedback Boundary Hardening
- M6.9 Continuation Curriculum
- M6.9.1 Curriculum Hardening
- M6.10 Discovery Value
- M6.11 Lawbook Acceptance Boundary
- M6.11.1 Public Surface / Terminology Hardening
- M6.12 Lawbook Query / Known Skip
- M6.13 Structural Identity
- M6.14 Habit Rules
- M6.15 Reason Compression
- M6.16 Process Memory
- M6.17 Structure Registry / Typed Projection
- M6.18 Role-Based Object Introduction
- M6.19 Structural Analogy / Exposition
- M6.20 Documentation / Spec Synchronization and Publication Refresh
- M7 Richer Formal-World Adapters
- M8 Deeper Proof-System Integration
- M9 Semantic and Natural-Language Claim Handling with Strict Boundaries
- M10 API Service Hardening
- M11 Existential Agent Ecology
- Post-M11 Hardening and Evaluation
- External Verifier Execution Adapter and Full End-to-End Test Drive
- Richer Verifier Adapter + Real Fixture Expansion
- Verified Corpus Micro-Ingestion
- Lean Project Micro-Subset Pilot
- CLI Import-Path Hardening + Colab Test Drive Script
- Mathlib Micro-Subset Pilot
- Real Local Mathlib Allowlist Pilot
- Mathlib Local Declaration Discovery + Allowlist Manifest Builder
- Curated Proof-Library Demo Pack + Optional Real Mathlib Allowlist Example
- Public Demo Notebook + Release Readiness + Optional Real Mathlib Revision Demo
- v0.1 Release Candidate Hardening
- Curated Real Mathlib Manifest v0 Demo
- Real Mathlib Module-Aware Verification v0
- Mathlib Module Verification v0.2 project execution hardening
- M12 Persistent Mathlib Digest Lawbook
- real curated Mathlib allowlist examples
- richer Lean parser / AST-backed extraction
- full Lean proof-term dependency extraction
- robust declaration-level dependency graph
- real induction constructor synthesis
- real leRecOn/order-recursion constructor synthesis
- dependency extraction through Lean tooling
- trusted importer policy for pinned external corpora
- richer Lake-aware diagnostics without network or package-manager actions
- API service endpoints over persistent Lawbook
- model-trained route/constructor ranking
- persistent Lawbook browser UI
- larger fixture-driven release gates
- persistent Lawbook storage workflow
- package/release workflow
Only verifier, trusted importer, finite validator, and chain audit boundaries promote truth. Every other layer is advisory unless it reports already accepted boundary evidence.