SOTAVerified

Mathematical Proofs

Papers

Showing 150 of 90 papers

TitleStatusHype
Prover Agent: An Agent-based Framework for Formal Mathematical Proofs0
The Alignment Trap: Complexity Barriers0
StepProof: Step-by-step verification of natural language mathematical proofsCode0
LeanTutor: A Formally-Verified AI Tutor for Mathematical Proofs0
Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations0
Identification of Probabilities of Causation: A Complete Characterization0
HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement0
Provably safe and human-like car-following behaviors: Part 2. A parsimonious multi-phase model with projected braking0
Neurodivergent Influenceability as a Contingent Solution to the AI Alignment Problem0
A Theoretical Analysis of Compositional Generalization in Neural Networks: A Necessary and Sufficient ConditionCode0
Hierarchical Attention Generates Better ProofsCode0
Statistical Guarantees in Synthetic Data through Conformal Adversarial Generation0
Mathematical Approach in Hybrid Beamforming for ISAC Systems0
Boundary Effects in Biological Planar Networks: Pentagons Dominate Marginal Cells0
Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection0
Theorem Prover as a Judge for Synthetic Data Generation0
Generating Millions Of Lean Theorems With Proofs By Exploring State Transition Graphs0
Efficient Long-Decoding Inference with Reasoning-Aware Attention Sparsity0
Automating Mathematical Proof Generation Using Large Language Model Agents and Knowledge Graphs0
LemmaHead: RAG Assisted Proof Generation Using Large Language Models0
Simple Proofs of the Summation and Connectivity Theorems in Metabolic Control Analysis0
Differentiable Convex Optimization Layers in Neural Architectures: Foundations and Perspectives0
Formal Language Knowledge Corpus for Retrieval Augmented Generation0
Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional RotationCode0
How Analysis Can Teach Us the Optimal Way to Design Neural Operators0
Learning Rules Explaining Interactive Theorem Proving Tactic PredictionCode0
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian SplattingsCode2
Gender Bias of LLM in Economics: An Existentialism Perspective0
FormalAlign: Automated Alignment Evaluation for AutoformalizationCode1
Mathematical Formalized Problem Solving and Theorem Proving in Different Fields in Lean 4Code0
Evolutionary Algorithms Are Significantly More Robust to Noise When They Ignore It0
Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph CompletionCode1
Examining the impact of forcing function inputs on structural identifiability0
SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic GradingCode0
Autograding Mathematical Induction Proofs with Natural Language Processing0
How Deduction Systems Can Help You To Verify Stability Properties0
A Semantic Search Engine for Mathlib40
Class Information Guided Reconstruction for Automatic Modulation Open-Set Recognition0
Automated Planning Techniques for Elementary Proofs in Abstract Algebra0
FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures0
Large Language Models' Understanding of Math: Source Criticism and Extrapolation0
Characterizing the Conditions for Indefinite Growth in Open Chemical Reaction Networks0
A New Approach Towards AutoformalizationCode0
Total-effect Test May Erroneously Reject So-called "Full" or "Complete" Mediation0
Anomaly zones for uniformly sampled gene trees under the gene duplication and loss model0
An Efficient Data Analysis Method for Big Data using Multiple-Model Linear Regression0
Algorithm-assisted discovery of an intrinsic order among mathematical constants0
CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation0
SmartDCA superiority0
TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation RotationCode1
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.