⊢ Logic - ch1n3du · Scour

ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning λType Theory

arxiv.org·1d

Partial functions and Church’s Thesis λType Theory

logicmatters.net·3d

SYNTHEX: Why Two Reasoning Streams Outperform One 🔍Interpretability

medium.com·19h

XENONOSTRA RESEARCH NOTES ALGEBROS-HG: A Graph-Grounded Hybrid Representation for Structural Code… ⚙️Compilers

medium.com·16h

Tax logic evaluation with Prolog · mthom scryer-prolog 📐Formal Methods

github.com·2d·Hacker News

Mergeable SNARGs for Trapdoor Languages and Their Applications 📐Formal Methods

eprint.iacr.org·3d

Giving LLMs a Formal Reasoning Engine for Code Analysis λType Theory

yogthos.net·1d·Lobsters, Hacker News

Beyond Opus: Decoding the “Dangerous” Reasoning of Claude Mythos 🏺Ancient History

medium.com

·1d

The spectrum of consistency strengths for membership in a computably enumerable set, Notre Dame Logic Seminar, April 2026 📐Formal Methods

jdh.hamkins.org·5d

Exploring capability gated out-of-context reasoning 🔍Interpretability

lesswrong.com·1d

806 Proofs, 44 Annotations: What grind Can and Can't Do 📐Formal Methods

alok.github.io·4d

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs 🔍Interpretability

arxiv.org·9h

What Is AI Inference? 🔍Interpretability

sambanova.ai·3d

Tri-System Theory 🌀Dynamical Systems

metafilter.com·5d

AI RESEARCH · REASONING 🔍Interpretability

medium.com·4d

Interactive Proofs [video] λType Theory

youtube.com·6d·Hacker News

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking 🔍Interpretability

arxiv.org·9h

Outsourcing Our Logical Thinking to Artificial Intelligence 🔍Interpretability

neatorama.com·4d

Inference Arena – new benchmark of local inference and training 🔍Interpretability

kvark.github.io·4d·Hacker News

A Decomposition Perspective to Long-context Reasoning for LLMs 🔍Interpretability

arxiv.org·9h

Loading more...