{"url":"/task/mathematical-proofs","name":"Mathematical Proofs","slug":"mathematical-proofs","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":90,"papers_with_code":29,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/naturalproofs","name":"NaturalProofs","full_name":"","num_papers_in_archive":13},{"url":"/dataset/holstep","name":"HolStep","full_name":"","num_papers_in_archive":10},{"url":"/dataset/constructivebench","name":"ConstructiveBench","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/automated-theorem-proving","name":"Automated Theorem Proving"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":29,"of":29,"tagged_in_all":90,"items":[{"url":"/paper/breastscreening-on-the-use-of-multi-modality","title":"BreastScreening: On the Use of Multi-Modality in Medical Imaging Diagnosis","date":"2020-04-07","arxiv_id":"2004.03500","repositories_listed":8,"syntology":null},{"url":"/paper/draft-sketch-and-prove-guiding-formal-theorem","title":"Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs","date":"2022-10-21","arxiv_id":"2210.12283","repositories_listed":3,"syntology":null},{"url":"/paper/transerr-translation-based-knowledge-graph","title":"TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation","date":"2023-06-26","arxiv_id":"2306.14580","repositories_listed":2,"syntology":null},{"url":"/paper/modelling-high-level-mathematical-reasoning","title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","date":"2020-06-13","arxiv_id":"2006.09265","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/adaswarm-a-novel-pso-optimization-method-for","title":"AdaSwarm: Augmenting Gradient-Based optimizers in Deep Learning with Swarm Intelligence","date":"2020-05-19","arxiv_id":"2006.09875","repositories_listed":2,"syntology":null},{"url":"/paper/2506-10558","title":"StepProof: Step-by-step verification of natural language mathematical proofs","date":"2025-06-12","arxiv_id":"2506.10558","repositories_listed":1,"syntology":null},{"url":"/paper/a-theoretical-analysis-of-compositional","title":"A Theoretical Analysis of Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition","date":"2025-05-05","arxiv_id":"2505.02627","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-attention-generates-better","title":"Hierarchical Attention Generates Better Proofs","date":"2025-04-27","arxiv_id":"2504.19188","repositories_listed":1,"syntology":null},{"url":"/paper/distance-adaptive-quaternion-knowledge-graph","title":"Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation","date":"2024-12-05","arxiv_id":"2412.04076","repositories_listed":1,"syntology":null},{"url":"/paper/learning-rules-explaining-interactive-theorem","title":"Learning Rules Explaining Interactive Theorem Proving Tactic Prediction","date":"2024-11-02","arxiv_id":"2411.01188","repositories_listed":1,"syntology":null},{"url":"/paper/odgs-3d-scene-reconstruction-from","title":"ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings","date":"2024-10-28","arxiv_id":"2410.20686","repositories_listed":1,"syntology":null},{"url":"/paper/formalalign-automated-alignment-evaluation","title":"FormalAlign: Automated Alignment Evaluation for Autoformalization","date":"2024-10-14","arxiv_id":"2410.10135","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/ai-for-mathematics-mathematical-formalized","title":"Mathematical Formalized Problem Solving and Theorem Proving in Different Fields in Lean 4","date":"2024-09-09","arxiv_id":"2409.05977","repositories_listed":1,"syntology":null},{"url":"/paper/simple-but-effective-compound-geometric","title":"Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion","date":"2024-08-13","arxiv_id":"2408.06603","repositories_listed":1,"syntology":null},{"url":"/paper/sciex-benchmarking-large-language-models-on","title":"SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading","date":"2024-06-14","arxiv_id":"2406.10421","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-approach-towards-autoformalization","title":"A New Approach Towards Autoformalization","date":"2023-10-12","arxiv_id":"2310.07957","repositories_listed":1,"syntology":null},{"url":"/paper/gentle-a-genre-diverse-multilayer-challenge","title":"GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation","date":"2023-06-03","arxiv_id":"2306.01966","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-era-in-software-security-towards-self","title":"A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification","date":"2023-05-24","arxiv_id":"2305.14752","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-relation-between-sharpness-aware","title":"Sharpness-Aware Minimization Alone can Improve Adversarial Robustness","date":"2023-05-09","arxiv_id":"2305.05392","repositories_listed":1,"syntology":null},{"url":"/paper/towards-autoformalization-of-mathematics-and","title":"Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs","date":"2023-01-05","arxiv_id":"2301.02195","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/formal-development-of-safe-automated-driving","title":"Formal Development of Safe Automated Driving using Differential Dynamic Logic","date":"2022-04-14","arxiv_id":"2204.06873","repositories_listed":1,"syntology":null},{"url":"/paper/calibration-of-p-values-for-calibration-and","title":"Calibration of P-values for calibration and for deviation of a subpopulation from the full population","date":"2022-01-31","arxiv_id":"2202.00100","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/theory-guided-hard-constraint-projection-hcp","title":"Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method","date":"2020-12-11","arxiv_id":"2012.06148","repositories_listed":1,"syntology":null},{"url":"/paper/differential-machine-learning","title":"Differential Machine Learning","date":"2020-05-05","arxiv_id":"2005.02347","repositories_listed":1,"syntology":null},{"url":"/paper/explosive-proofs-of-mathematical-truths","title":"Epistemic Phase Transitions in Mathematical Proofs","date":"2020-03-31","arxiv_id":"2004.00055","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-prove-theorems-via-interacting","title":"Learning to Prove Theorems via Interacting with Proof Assistants","date":"2019-05-21","arxiv_id":"1905.09381","repositories_listed":1,"syntology":null},{"url":"/paper/-rank-multi-agent-evaluation-by-evolution","title":"α-Rank: Multi-Agent Evaluation by Evolution","date":"2019-03-04","arxiv_id":"1903.01373","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-parallel-algorithm-for-regularized","title":"A Unified Parallel Algorithm for Regularized Group PLS Scalable to Big Data","date":"2017-02-23","arxiv_id":"1702.07066","repositories_listed":1,"syntology":null},{"url":"/paper/premise-selection-for-mathematics-by-corpus","title":"Premise Selection for Mathematics by Corpus Analysis and Kernel Methods","date":"2011-08-17","arxiv_id":"1108.3446","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}