A top-level contract tells you what a system does. Sub-contracts tell the prover how it does it. You only need to read the first one. This is componentisation in real terms — and it changes how we thi...

We proved type preservation for PCF — a classic typed lambda calculus benchmark — using two frontier LLMs and rocq-piler. DeepSeek v4 completed it in 21 minutes for $0.06. Claude Opus 4.8 took 14 minu...

We proved type preservation for PCF — a classic typed lambda calculus benchmark — using two frontier LLMs and rocq-piler. DeepSeek v4 completed it in 21 minutes for $0.06. Claude Opus 4.8 took 14 minu...

We proved type preservation for PCF — a classic typed lambda calculus benchmark — using two frontier LLMs and rocq-piler. DeepSeek v4 completed it in 21 minutes for $0.06. Claude Opus 4.8 took 14 minu...

MCP server for Coq LSP. Contribute to scidonia/rocq-piler development by creating an account on GitHub.

Most software developers haven't twigged the real potential of automated theorem proving with LLMs. If provers are powerful enough, you no longer need to understand the code — only the contracts at th...

MCP server for Coq LSP. Contribute to scidonia/rocq-piler development by creating an account on GitHub.

MCP server for Coq LSP. Contribute to scidonia/mcp-coq-lsp development by creating an account on GitHub.

Every extraction pipeline needs a verification step. We tested eight models as quality scorers and found that for hallucination detection, a model costing 200× less than Claude performs identically. B...

Giving an LLM a typed, navigable knowledge structure instead of a flat scratchpad changes what it can remember, how it updates facts, and how much context it consumes doing so.

String matching cannot tell you whether an LLM remembers what was said in a conversation. We describe the QA-probing methodology we use to measure short-term memory recall and wiki precision, and what...

Hallucinated entities and relationships look identical to real ones inside a knowledge graph. We measured how often frontier models inject facts from parametric memory rather than from your documents ...

We ran three frontier models on 8 open-licence documents and measured how accurately each one identifies named people — before and after cross-checking. The results reveal meaningful differences in hallucination rates and the value of verification.

MCP server for Coq LSP. Contribute to scidonia/mcp-coq-lsp development by creating an account on GitHub.