repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 5h ago
sileod/reasoning-core
Procedural data generators for verifiable reasoning, synthetic pretraining, post-training, evaluation, and RL.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing →
- PossiblePossibly related (embedding) · 54%Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers →
- PossiblePossibly related (embedding) · 53%Generative Skill Composition for LLM Agents →
- PossiblePossibly related (embedding) · 53%Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination →
- PossiblePossibly related (embedding) · 51%Northwind AI →
- PossiblePossibly related (embedding) · 53%TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B →
- PossiblePossibly related (embedding) · 50%G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models →
- PossiblePossibly related (embedding) · 55%Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs →
Implements
paperVerifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem ProposingpaperBridging the Gap Between Latent and Explicit Reasoning with Looped TransformerspaperGenerative Skill Composition for LLM AgentspaperGraph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Related to
Implements (incoming)
paperTUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27BpaperG-RRM: Guiding Symbolic Solvers with Recurrent Reasoning ModelspaperFormal Disco: Scalable Open-Ended Generation of Formally Verified ProgramspaperPluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource LanguagespaperDT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety GuardrailpaperHarnessing Code Agents for Automatic Software VerificationpaperMitigating Domain Shift in Conditioned Floor Plan Generation: Synthetic Pre-training for Data-Efficient AdaptationpaperProjAgent: Procedural Similarity Retrieval for Repository-Level Code GenerationpaperEvidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel ProofspaperLLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with ElenchospaperRing-Zero: Scaling Zero RL to a Trillion Parameters for Emergent ReasoningpaperLearning Mechanistic Reasoning for Chemical Reactions with Large Language ModelspaperFormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem GenerationpaperAdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and VerificationpaperThink Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
Covers (incoming)
Related across the graph
paperLearning Mechanistic Reasoning for Chemical Reactions with Large Language ModelspaperVerifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem ProposingpaperG-RRM: Guiding Symbolic Solvers with Recurrent Reasoning ModelspaperDT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety GuardrailcompanyNorthwind AIpaperGenerative Skill Composition for LLM AgentsnewsExploring self-distilled reasoning for supervised fine-tuning with Amazon NovapaperHarnessing Code Agents for Automatic Software VerificationpaperMitigating Domain Shift in Conditioned Floor Plan Generation: Synthetic Pre-training for Data-Efficient AdaptationpaperEvidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel ProofspaperPluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource LanguagespaperRing-Zero: Scaling Zero RL to a Trillion Parameters for Emergent ReasoningpaperThink Through a Bottleneck: Hourglass Reasoning for Rigorous InductionpaperAdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and VerificationpaperProjAgent: Procedural Similarity Retrieval for Repository-Level Code GenerationpaperFormal Disco: Scalable Open-Ended Generation of Formally Verified ProgramspaperFormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem GenerationnewsCLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning - Apple Machine Learning ResearchpaperTUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27BpaperBridging the Gap Between Latent and Explicit Reasoning with Looped TransformerspaperGraph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual RecombinationpaperLLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos