{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/automated-theorem-proving","name":"Automated Theorem Proving","slug":"automated-theorem-proving","description_markdown":"The goal of **Automated Theorem Proving** is to automatically generate a proof, given a conjecture (the target theorem) and a knowledge base of known facts, all expressed in a formal language. Automated Theorem Proving is useful in a wide range of applications, including the verification and synthesis of software and hardware systems.\r\n\r\n\r\n<span class=\"description-source\">Source: [Learning to Prove Theorems by Learning to Generate Theorems ](https://arxiv.org/abs/2002.07019)</span>","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":288,"papers_with_code":110,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"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":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","slug":"automated-theorem-proving-on-minif2f-test","dataset":"miniF2F-test","dataset_url":"/dataset/minif2f","rows_in_archive":29,"metrics":["cumulative","Pass@1","Pass@32","Pass@64","Pass@100","ITP","pass@1024","pass@8192"],"first_row_in_archive_order":{"model":"Kimina-Prover-Preview","paper_title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","paper_url":"/paper/kimina-prover-preview-towards-large-formal","paper_date":"2025-04-15","arxiv_id":"2504.11354","code_links":[{"title":"moonshotai/kimina-prover-preview","url":"https://github.com/moonshotai/kimina-prover-preview"},{"title":"cmu-l3/llmlean","url":"https://github.com/cmu-l3/llmlean"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kimina-prover-preview-towards-large-formal#ran","syntology_url":"https://syntology.ai/paper/2504.11354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11354"}},"official":{"repos":["moonshotai/kimina-prover-preview"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-valid","slug":"automated-theorem-proving-on-minif2f-valid","dataset":"miniF2F-valid","dataset_url":"/dataset/minif2f","rows_in_archive":10,"metrics":["Pass@8","Pass@64","Pass@1","Pass@100"],"first_row_in_archive_order":{"model":"Lean GPT-f","paper_title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","paper_url":"/paper/minif2f-a-cross-system-benchmark-for-formal","paper_date":"2021-08-31","arxiv_id":"2109.00110","code_links":[{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"yangky11/minif2f-lean4","url":"https://github.com/yangky11/minif2f-lean4"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minif2f-a-cross-system-benchmark-for-formal#ran","syntology_url":"https://syntology.ai/paper/2109.00110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00110"}},"official":{"repos":["openai/minif2f"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/automated-theorem-proving-on-holstep","slug":"automated-theorem-proving-on-holstep","dataset":"HolStep (Conditional)","dataset_url":"/dataset/holstep","rows_in_archive":5,"metrics":["Classification Accuracy"],"first_row_in_archive_order":{"model":"MPNN-DagLSTM","paper_title":"Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling","paper_url":"/paper/improving-graph-neural-network","paper_date":"2019-11-15","arxiv_id":"1911.06904","code_links":[{"title":"IBM/LogicalFormulaEmbedder","url":"https://github.com/IBM/LogicalFormulaEmbedder"}],"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improving-graph-neural-network#ran","syntology_url":"https://syntology.ai/paper/1911.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06904"}},"official":null}}},{"leaderboard":"/sota/automated-theorem-proving-on-holist-benchmark","slug":"automated-theorem-proving-on-holist-benchmark","dataset":"HOList benchmark","dataset_url":"/dataset/holist","rows_in_archive":4,"metrics":["Percentage correct"],"first_row_in_archive_order":{"model":"4-hop GNN, sub-expression sharing","paper_title":"Graph Representations for Higher-Order Logic and Theorem Proving","paper_url":"/paper/graph-representations-for-higher-order-logic","paper_date":"2019-05-24","arxiv_id":"1905.10006","code_links":[],"syntology":null}},{"leaderboard":"/sota/automated-theorem-proving-on-holstep-1","slug":"automated-theorem-proving-on-holstep-1","dataset":"HolStep (Unconditional)","dataset_url":"/dataset/holstep","rows_in_archive":4,"metrics":["Classification Accuracy"],"first_row_in_archive_order":{"model":"FormulaNet","paper_title":"Premise Selection for Theorem Proving by Deep Graph Embedding","paper_url":"/paper/premise-selection-for-theorem-proving-by-deep","paper_date":"2017-09-28","arxiv_id":"1709.09994","code_links":[{"title":"princeton-vl/FormulaNet","url":"https://github.com/princeton-vl/FormulaNet"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/premise-selection-for-theorem-proving-by-deep#ran","syntology_url":"https://syntology.ai/paper/1709.09994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.09994"}},"official":{"repos":["princeton-vl/FormulaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/automated-theorem-proving-on-metamath-setmm","slug":"automated-theorem-proving-on-metamath-setmm","dataset":"Metamath set.mm","dataset_url":null,"rows_in_archive":4,"metrics":["Percentage correct","Pass@32"],"first_row_in_archive_order":{"model":"GPT-f","paper_title":"Generative Language Modeling for Automated Theorem Proving","paper_url":"/paper/generative-language-modeling-for-automated","paper_date":"2020-09-07","arxiv_id":"2009.03393","code_links":[],"syntology":null}},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-1","slug":"automated-theorem-proving-on-minif2f-1","dataset":"miniF2F-curriculum","dataset_url":null,"rows_in_archive":4,"metrics":["Pass@64"],"first_row_in_archive_order":{"model":"Evariste-7d","paper_title":"HyperTree Proof Search for Neural Theorem Proving","paper_url":"/paper/hypertree-proof-search-for-neural-theorem","paper_date":"2022-05-23","arxiv_id":"2205.11491","code_links":[],"syntology":null}},{"leaderboard":"/sota/automated-theorem-proving-on-compcert","slug":"automated-theorem-proving-on-compcert","dataset":"CompCert","dataset_url":null,"rows_in_archive":2,"metrics":["Percentage correct"],"first_row_in_archive_order":{"model":"Proverbot9001","paper_title":"Generating Correctness Proofs with Neural Networks","paper_url":"/paper/generating-correctness-proofs-with-neural-1","paper_date":"2020-05-28","arxiv_id":"1907.07794","code_links":[{"title":"UCSD-PL/proverbot9001","url":"https://github.com/UCSD-PL/proverbot9001"}],"syntology":null}},{"leaderboard":"/sota/automated-theorem-proving-on-coqgym","slug":"automated-theorem-proving-on-coqgym","dataset":"CoqGym","dataset_url":null,"rows_in_archive":1,"metrics":["Percentage correct"],"first_row_in_archive_order":{"model":"ASTactic","paper_title":"Learning to Prove Theorems via Interacting with Proof Assistants","paper_url":"/paper/learning-to-prove-theorems-via-interacting","paper_date":"2019-05-21","arxiv_id":"1905.09381","code_links":[{"title":"princeton-vl/CoqGym","url":"https://github.com/princeton-vl/CoqGym"}],"syntology":null}}],"datasets":[{"url":"/dataset/minif2f","name":"MiniF2F","full_name":"","num_papers_in_archive":84},{"url":"/dataset/geometry3k","name":"Geometry3K","full_name":"","num_papers_in_archive":45},{"url":"/dataset/proofnet","name":"ProofNet","full_name":"","num_papers_in_archive":27},{"url":"/dataset/med","name":"MED","full_name":"Monotonicity Entailment Dataset","num_papers_in_archive":18},{"url":"/dataset/holstep","name":"HolStep","full_name":"","num_papers_in_archive":10},{"url":"/dataset/kinship","name":"Kinship","full_name":null,"num_papers_in_archive":10},{"url":"/dataset/holist","name":"HOList","full_name":"HOList","num_papers_in_archive":8},{"url":"/dataset/gamepad-environment","name":"GamePad Environment","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/mathematical-proofs","name":"Mathematical Proofs"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":288,"of_with_code":110,"tagged_in_all":288,"counts":{"archive_papers_tagged":288,"with_a_code_link":110,"where_syntology_ran_a_sample":46,"not_listed_spam_title":0,"listed":288,"listed_where_code_ran":46,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":34,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":34,"listed_every_run_a_failure_of_syntologys_instrument":12,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/minictx-neural-theorem-proving-with-long","slug":"minictx-neural-theorem-proving-with-long","title":"miniCTX: Neural Theorem Proving with (Long-)Contexts","date":"2024-08-05","arxiv_id":"2408.03350","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minictx-neural-theorem-proving-with-long#ran","syntology_url":"https://syntology.ai/paper/2408.03350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03350"}},"official":{"repos":["cmu-l3/minictx-eval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llemma-an-open-language-model-for-mathematics","slug":"llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}},"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/minif2f-a-cross-system-benchmark-for-formal","slug":"minif2f-a-cross-system-benchmark-for-formal","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","date":"2021-08-31","arxiv_id":"2109.00110","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minif2f-a-cross-system-benchmark-for-formal#ran","syntology_url":"https://syntology.ai/paper/2109.00110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00110"}},"official":{"repos":["openai/minif2f"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/proof-artifact-co-training-for-theorem","slug":"proof-artifact-co-training-for-theorem","title":"Proof Artifact Co-training for Theorem Proving with Language Models","date":"2021-02-11","arxiv_id":"2102.06203","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/proof-artifact-co-training-for-theorem#ran","syntology_url":"https://syntology.ai/paper/2102.06203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06203"}},"official":{"repos":["jasonrute/lean-proof-recording-public","jasonrute/lean_proof_recording","jesse-michael-han/lean-step-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/holophrasm-a-neural-automated-theorem-prover","slug":"holophrasm-a-neural-automated-theorem-prover","title":"Holophrasm: a neural Automated Theorem Prover for higher-order logic","date":"2016-08-08","arxiv_id":"1608.02644","repositories_listed":4,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/holophrasm-a-neural-automated-theorem-prover#ran","syntology_url":"https://syntology.ai/paper/1608.02644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.02644"}},"official":{"repos":["dwhalen/holophrasm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/leandojo-theorem-proving-with-retrieval-1","slug":"leandojo-theorem-proving-with-retrieval-1","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","date":"2023-06-27","arxiv_id":"2306.15626","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leandojo-theorem-proving-with-retrieval-1#ran","syntology_url":"https://syntology.ai/paper/2306.15626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15626"}},"official":{"repos":["lean-dojo/leandojo","lean-dojo/leandojochatgpt","lean-dojo/reprover"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/draft-sketch-and-prove-guiding-formal-theorem","slug":"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/holist-an-environment-for-machine-learning-of","slug":"holist-an-environment-for-machine-learning-of","title":"HOList: An Environment for Machine Learning of Higher-Order Theorem Proving","date":"2019-04-05","arxiv_id":"1904.03241","repositories_listed":3,"syntology":null},{"url":"/paper/deeptheorem-advancing-llm-reasoning-for","slug":"deeptheorem-advancing-llm-reasoning-for","title":"DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning","date":"2025-05-29","arxiv_id":"2505.23754","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deeptheorem-advancing-llm-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2505.23754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23754"}},"official":{"repos":["jiahao004/deeptheorem"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kimina-prover-preview-towards-large-formal","slug":"kimina-prover-preview-towards-large-formal","title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","date":"2025-04-15","arxiv_id":"2504.11354","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kimina-prover-preview-towards-large-formal#ran","syntology_url":"https://syntology.ai/paper/2504.11354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11354"}},"official":{"repos":["moonshotai/kimina-prover-preview"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rm-p-small-roof-w-small-ala-multilingual","slug":"rm-p-small-roof-w-small-ala-multilingual","title":"ProofWala: Multilingual Proof Data Synthesis and Theorem-Proving","date":"2025-02-07","arxiv_id":"2502.04671","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rm-p-small-roof-w-small-ala-multilingual#ran","syntology_url":"https://syntology.ai/paper/2502.04671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04671"}},"official":{"repos":["trishullab/itp-interface","trishullab/proof-wala"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pantograph-a-machine-to-machine-interaction","slug":"pantograph-a-machine-to-machine-interaction","title":"Pantograph: A Machine-to-Machine Interaction Interface for Advanced Theorem Proving, High Level Reasoning, and Data Extraction in Lean 4","date":"2024-10-21","arxiv_id":"2410.16429","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pantograph-a-machine-to-machine-interaction#ran","syntology_url":"https://syntology.ai/paper/2410.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16429"}},"official":{"repos":["lenianiva/pypantograph","stanford-centaur/pypantograph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepseek-prover-v1-5-harnessing-proof","slug":"deepseek-prover-v1-5-harnessing-proof","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","date":"2024-08-15","arxiv_id":"2408.08152","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepseek-prover-v1-5-harnessing-proof#ran","syntology_url":"https://syntology.ai/paper/2408.08152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08152"}},"official":{"repos":["deepseek-ai/deepseek-prover-v1.5"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/putnambench-evaluating-neural-theorem-provers","slug":"putnambench-evaluating-neural-theorem-provers","title":"PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition","date":"2024-07-15","arxiv_id":"2407.11214","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/putnambench-evaluating-neural-theorem-provers#ran","syntology_url":"https://syntology.ai/paper/2407.11214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11214"}},"official":{"repos":["trishullab/putnam","trishullab/putnambench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-formal-mathematics-from-intrinsic","slug":"learning-formal-mathematics-from-intrinsic","title":"Learning Formal Mathematics From Intrinsic Motivation","date":"2024-06-30","arxiv_id":"2407.00695","repositories_listed":2,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/learning-formal-mathematics-from-intrinsic#ran","syntology_url":"https://syntology.ai/paper/2407.00695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00695"}},"official":{"repos":["gpoesia/minimo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-large-language-models-as-copilots-for","slug":"towards-large-language-models-as-copilots-for","title":"Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean","date":"2024-04-18","arxiv_id":"2404.12534","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-large-language-models-as-copilots-for#ran","syntology_url":"https://syntology.ai/paper/2404.12534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12534"}},"official":{"repos":["lean-dojo/leancopilot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/proofnet-autoformalizing-and-formally-proving","slug":"proofnet-autoformalizing-and-formally-proving","title":"ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics","date":"2023-02-24","arxiv_id":"2302.12433","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/proofnet-autoformalizing-and-formally-proving#ran","syntology_url":"https://syntology.ai/paper/2302.12433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12433"}},"official":{"repos":["eleutherai/gpt-neox","zhangir-azerbayev/proofnet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/linear-algebra-with-transformers-1","slug":"linear-algebra-with-transformers-1","title":"Linear algebra with transformers","date":"2021-12-03","arxiv_id":"2112.01898","repositories_listed":2,"syntology":null},{"url":"/paper/learning-symbolic-rules-for-reasoning-in-1","slug":"learning-symbolic-rules-for-reasoning-in-1","title":"Learning Symbolic Rules for Reasoning in Quasi-Natural Language","date":"2021-11-23","arxiv_id":"2111.12038","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-match-mathematical-statements","slug":"learning-to-match-mathematical-statements","title":"Learning to Match Mathematical Statements with Proofs","date":"2021-02-03","arxiv_id":"2102.02110","repositories_listed":2,"syntology":null},{"url":"/paper/measuring-systematic-generalization-in-neural","slug":"measuring-systematic-generalization-in-neural","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","date":"2020-09-30","arxiv_id":"2009.14786","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-systematic-generalization-in-neural#ran","syntology_url":"https://syntology.ai/paper/2009.14786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14786"}},"official":{"repos":["NicolasAG/SGinPG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/logical-neural-networks","slug":"logical-neural-networks","title":"Logical Neural Networks","date":"2020-06-23","arxiv_id":"2006.13155","repositories_listed":2,"syntology":{"n":15,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":13,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/logical-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2006.13155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13155"}},"official":{"repos":["IBM/LNN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-prove-theorems-by-learning-to-1","slug":"learning-to-prove-theorems-by-learning-to-1","title":"Learning to Prove Theorems by Learning to Generate Theorems","date":"2020-02-17","arxiv_id":"2002.07019","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-to-prove-theorems-by-learning-to-1#ran","syntology_url":"https://syntology.ai/paper/2002.07019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07019"}},"official":{"repos":["princeton-vl/MetaGen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/deepmath-deep-sequence-models-for-premise","slug":"deepmath-deep-sequence-models-for-premise","title":"DeepMath - Deep Sequence Models for Premise Selection","date":"2016-06-14","arxiv_id":"1606.04442","repositories_listed":2,"syntology":null},{"url":"/paper/criticlean-critic-guided-reinforcement","slug":"criticlean-critic-guided-reinforcement","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","date":"2025-07-08","arxiv_id":"2507.06181","repositories_listed":1,"syntology":null},{"url":"/paper/safe-enhancing-mathematical-reasoning-in","slug":"safe-enhancing-mathematical-reasoning-in","title":"Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification","date":"2025-06-05","arxiv_id":"2506.04592","repositories_listed":1,"syntology":null},{"url":"/paper/leanexplore-a-search-engine-for-lean-4","slug":"leanexplore-a-search-engine-for-lean-4","title":"LeanExplore: A search engine for Lean 4 declarations","date":"2025-06-04","arxiv_id":"2506.11085","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leanexplore-a-search-engine-for-lean-4#ran","syntology_url":"https://syntology.ai/paper/2506.11085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.11085"}},"official":{"repos":["justincasher/lean-explore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/autoformalization-in-the-era-of-large","slug":"autoformalization-in-the-era-of-large","title":"Autoformalization in the Era of Large Language Models: A Survey","date":"2025-05-29","arxiv_id":"2505.23486","repositories_listed":1,"syntology":null},{"url":"/paper/enumerate-conjecture-prove-formally-solving","slug":"enumerate-conjecture-prove-formally-solving","title":"Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions","date":"2025-05-24","arxiv_id":"2505.18492","repositories_listed":1,"syntology":null},{"url":"/paper/mirb-mathematical-information-retrieval","slug":"mirb-mathematical-information-retrieval","title":"MIRB: Mathematical Information Retrieval Benchmark","date":"2025-05-21","arxiv_id":"2505.15585","repositories_listed":1,"syntology":null},{"url":"/paper/ineq-comp-benchmarking-human-intuitive","slug":"ineq-comp-benchmarking-human-intuitive","title":"Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities","date":"2025-05-19","arxiv_id":"2505.12680","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ineq-comp-benchmarking-human-intuitive#ran","syntology_url":"https://syntology.ai/paper/2505.12680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12680"}},"official":{"repos":["haoyuzhao123/leanineqcomp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-based-automated-theorem-proving-hinges-on","slug":"llm-based-automated-theorem-proving-hinges-on","title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation","date":"2025-05-17","arxiv_id":"2505.12031","repositories_listed":1,"syntology":null},{"url":"/paper/deepseek-prover-v2-advancing-formal","slug":"deepseek-prover-v2-advancing-formal","title":"DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition","date":"2025-04-30","arxiv_id":"2504.21801","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-attention-generates-better","slug":"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/leanabell-prover-posttraining-scaling-in","slug":"leanabell-prover-posttraining-scaling-in","title":"Leanabell-Prover: Posttraining Scaling in Formal Reasoning","date":"2025-04-08","arxiv_id":"2504.06122","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-mathematical-reasoning-and","slug":"a-survey-on-mathematical-reasoning-and","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","date":"2025-03-22","arxiv_id":"2503.17726","repositories_listed":1,"syntology":null},{"url":"/paper/ma-lot-multi-agent-lean-based-long-chain-of","slug":"ma-lot-multi-agent-lean-based-long-chain-of","title":"MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving","date":"2025-03-05","arxiv_id":"2503.03205","repositories_listed":1,"syntology":null},{"url":"/paper/goedel-prover-a-frontier-model-for-open","slug":"goedel-prover-a-frontier-model-for-open","title":"Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving","date":"2025-02-11","arxiv_id":"2502.07640","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/goedel-prover-a-frontier-model-for-open#ran","syntology_url":"https://syntology.ai/paper/2502.07640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07640"}},"official":{"repos":["Goedel-LM/Goedel-Prover"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stp-self-play-llm-theorem-provers-with","slug":"stp-self-play-llm-theorem-provers-with","title":"STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving","date":"2025-01-31","arxiv_id":"2502.00212","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/stp-self-play-llm-theorem-provers-with#ran","syntology_url":"https://syntology.ai/paper/2502.00212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00212"}},"official":{"repos":["kfdong/STP"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-neural-theorem-proving-via-fine","slug":"efficient-neural-theorem-proving-via-fine","title":"Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis","date":"2025-01-30","arxiv_id":"2501.18310","repositories_listed":1,"syntology":null},{"url":"/paper/withdrarxiv-a-large-scale-dataset-for","slug":"withdrarxiv-a-large-scale-dataset-for","title":"WithdrarXiv: A Large-Scale Dataset for Retraction Study","date":"2024-12-04","arxiv_id":"2412.03775","repositories_listed":1,"syntology":null},{"url":"/paper/learning-rules-explaining-interactive-theorem","slug":"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/beyond-autoregression-fast-llms-via-self","slug":"beyond-autoregression-fast-llms-via-self","title":"Beyond Autoregression: Fast LLMs via Self-Distillation Through Time","date":"2024-10-28","arxiv_id":"2410.21035","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-autoregression-fast-llms-via-self#ran","syntology_url":"https://syntology.ai/paper/2410.21035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21035"}},"official":{"repos":["jdeschena/sdtt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/alchemy-amplifying-theorem-proving-capability","slug":"alchemy-amplifying-theorem-proving-capability","title":"Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation","date":"2024-10-21","arxiv_id":"2410.15748","repositories_listed":1,"syntology":null},{"url":"/paper/internlm2-5-stepprover-advancing-automated","slug":"internlm2-5-stepprover-advancing-automated","title":"InternLM2.5-StepProver: Advancing Automated Theorem Proving via Expert Iteration on Large-Scale LEAN Problems","date":"2024-10-21","arxiv_id":"2410.15700","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/internlm2-5-stepprover-advancing-automated#ran","syntology_url":"https://syntology.ai/paper/2410.15700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15700"}},"official":{"repos":["internlm/internlm-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leanagent-lifelong-learning-for-formal","slug":"leanagent-lifelong-learning-for-formal","title":"LeanAgent: Lifelong Learning for Formal Theorem Proving","date":"2024-10-08","arxiv_id":"2410.06209","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/leanagent-lifelong-learning-for-formal#ran","syntology_url":"https://syntology.ai/paper/2410.06209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06209"}},"official":null}},{"url":"/paper/ai-for-mathematics-mathematical-formalized","slug":"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/subgoalxl-subgoal-based-expert-learning-for","slug":"subgoalxl-subgoal-based-expert-learning-for","title":"SubgoalXL: Subgoal-based Expert Learning for Theorem Proving","date":"2024-08-20","arxiv_id":"2408.11172","repositories_listed":1,"syntology":null},{"url":"/paper/lean-github-compiling-github-lean","slug":"lean-github-compiling-github-lean","title":"LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover","date":"2024-07-24","arxiv_id":"2407.17227","repositories_listed":1,"syntology":null},{"url":"/paper/theoremllama-transforming-general-purpose","slug":"theoremllama-transforming-general-purpose","title":"TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts","date":"2024-07-03","arxiv_id":"2407.03203","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/theoremllama-transforming-general-purpose#ran","syntology_url":"https://syntology.ai/paper/2407.03203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03203"}},"official":{"repos":["RickySkywalker/TheoremLlama"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fvel-interactive-formal-verification","slug":"fvel-interactive-formal-verification","title":"FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving","date":"2024-06-20","arxiv_id":"2406.14408","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fvel-interactive-formal-verification#ran","syntology_url":"https://syntology.ai/paper/2406.14408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14408"}},"official":{"repos":["fveler/fvel"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-synthetic-logical-reasoning-datasets","slug":"scaling-synthetic-logical-reasoning-datasets","title":"Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars","date":"2024-06-16","arxiv_id":"2406.11035","repositories_listed":1,"syntology":null},{"url":"/paper/lean-workbook-a-large-scale-lean-problem-set","slug":"lean-workbook-a-large-scale-lean-problem-set","title":"Lean Workbook: A large-scale Lean problem set formalized from natural language math problems","date":"2024-06-06","arxiv_id":"2406.03847","repositories_listed":1,"syntology":null},{"url":"/paper/proving-theorems-recursively","slug":"proving-theorems-recursively","title":"Proving Theorems Recursively","date":"2024-05-23","arxiv_id":"2405.14414","repositories_listed":1,"syntology":null},{"url":"/paper/verification-and-refinement-of-natural","slug":"verification-and-refinement-of-natural","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","date":"2024-05-02","arxiv_id":"2405.01379","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/verification-and-refinement-of-natural#ran","syntology_url":"https://syntology.ai/paper/2405.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01379"}},"official":{"repos":["neuro-symbolic-ai/explanation_refinement"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-deep-learning-for-theorem-proving","slug":"a-survey-on-deep-learning-for-theorem-proving","title":"A Survey on Deep Learning for Theorem Proving","date":"2024-04-15","arxiv_id":"2404.09939","repositories_listed":1,"syntology":null},{"url":"/paper/learn-from-failure-fine-tuning-llms-with","slug":"learn-from-failure-fine-tuning-llms-with","title":"Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving","date":"2024-04-10","arxiv_id":"2404.07382","repositories_listed":1,"syntology":null},{"url":"/paper/don-t-trust-verify-grounding-llm-quantitative","slug":"don-t-trust-verify-grounding-llm-quantitative","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","date":"2024-03-26","arxiv_id":"2403.18120","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/don-t-trust-verify-grounding-llm-quantitative#ran","syntology_url":"https://syntology.ai/paper/2403.18120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18120"}},"official":{"repos":["jinpz/dtv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/leanreasoner-boosting-complex-logical","slug":"leanreasoner-boosting-complex-logical","title":"LeanReasoner: Boosting Complex Logical Reasoning with Lean","date":"2024-03-20","arxiv_id":"2403.13312","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leanreasoner-boosting-complex-logical#ran","syntology_url":"https://syntology.ai/paper/2403.13312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13312"}},"official":{"repos":["some-random/theorem-proving-reasoning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-in-feasibility-of-ml-backdoor","slug":"on-the-in-feasibility-of-ml-backdoor","title":"On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem","date":"2024-02-26","arxiv_id":"2402.16926","repositories_listed":1,"syntology":null},{"url":"/paper/refactor-learning-to-extract-theorems-from-1","slug":"refactor-learning-to-extract-theorems-from-1","title":"REFACTOR: Learning to Extract Theorems from Proofs","date":"2024-02-26","arxiv_id":"2402.17032","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/refactor-learning-to-extract-theorems-from-1#ran","syntology_url":"https://syntology.ai/paper/2402.17032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17032"}},"official":{"repos":["jinpz/refactor"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-of-data-ability-boundary","slug":"an-empirical-study-of-data-ability-boundary","title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","date":"2024-02-23","arxiv_id":"2403.00799","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-empirical-study-of-data-ability-boundary#ran","syntology_url":"https://syntology.ai/paper/2403.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00799"}},"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mustard-mastering-uniform-synthesis-of","slug":"mustard-mastering-uniform-synthesis-of","title":"MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data","date":"2024-02-14","arxiv_id":"2402.08957","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mustard-mastering-uniform-synthesis-of#ran","syntology_url":"https://syntology.ai/paper/2402.08957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08957"}},"official":{"repos":["eleanor-h/mustard"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-completion-of-statements-and-proofs","slug":"automated-completion-of-statements-and-proofs","title":"Automated Completion of Statements and Proofs in Synthetic Geometry: an Approach based on Constraint Solving","date":"2024-01-22","arxiv_id":"2401.11898","repositories_listed":1,"syntology":null},{"url":"/paper/trigo-benchmarking-formal-mathematical-proof","slug":"trigo-benchmarking-formal-mathematical-proof","title":"TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models","date":"2023-10-16","arxiv_id":"2310.10180","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/trigo-benchmarking-formal-mathematical-proof#ran","syntology_url":"https://syntology.ai/paper/2310.10180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10180"}},"official":{"repos":["menik1126/TRIGO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-language-agent-approach-to-formal-theorem","slug":"a-language-agent-approach-to-formal-theorem","title":"An In-Context Learning Agent for Formal Theorem-Proving","date":"2023-10-06","arxiv_id":"2310.04353","repositories_listed":1,"syntology":null},{"url":"/paper/lego-prover-neural-theorem-proving-with","slug":"lego-prover-neural-theorem-proving-with","title":"LEGO-Prover: Neural Theorem Proving with Growing Libraries","date":"2023-10-01","arxiv_id":"2310.00656","repositories_listed":1,"syntology":null},{"url":"/paper/lyra-orchestrating-dual-correction-in","slug":"lyra-orchestrating-dual-correction-in","title":"Lyra: Orchestrating Dual Correction in Automated Theorem Proving","date":"2023-09-27","arxiv_id":"2309.15806","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lyra-orchestrating-dual-correction-in#ran","syntology_url":"https://syntology.ai/paper/2309.15806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15806"}},"official":{"repos":["chuanyang-zheng/lyra-theorem-prover"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fimo-a-challenge-formal-dataset-for-automated","slug":"fimo-a-challenge-formal-dataset-for-automated","title":"FIMO: A Challenge Formal Dataset for Automated Theorem Proving","date":"2023-09-08","arxiv_id":"2309.04295","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-the-enigma-subgoal-based","slug":"decomposing-the-enigma-subgoal-based","title":"Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving","date":"2023-05-25","arxiv_id":"2305.16366","repositories_listed":1,"syntology":null},{"url":"/paper/theorem-proving-in-dependently-typed-higher","slug":"theorem-proving-in-dependently-typed-higher","title":"Theorem Proving in Dependently-Typed Higher-Order Logic -- Extended Preprint","date":"2023-05-24","arxiv_id":"2305.15382","repositories_listed":1,"syntology":null},{"url":"/paper/an-ensemble-approach-for-automated-theorem","slug":"an-ensemble-approach-for-automated-theorem","title":"An Ensemble Approach for Automated Theorem Proving Based on Efficient Name Invariant Graph Neural Representations","date":"2023-05-15","arxiv_id":"2305.08676","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/an-ensemble-approach-for-automated-theorem#ran","syntology_url":"https://syntology.ai/paper/2305.08676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08676"}},"official":{"repos":["IBM/TRAIL"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/lemmas-generation-selection-application","slug":"lemmas-generation-selection-application","title":"Lemmas: Generation, Selection, Application","date":"2023-03-10","arxiv_id":"2303.05854","repositories_listed":1,"syntology":null},{"url":"/paper/parsel-a-unified-natural-language-framework","slug":"parsel-a-unified-natural-language-framework","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","date":"2022-12-20","arxiv_id":"2212.10561","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parsel-a-unified-natural-language-framework#ran","syntology_url":"https://syntology.ai/paper/2212.10561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10561"}},"official":{"repos":["ezelikman/parsel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-qmltp-problems-by-translation-to","slug":"solving-qmltp-problems-by-translation-to","title":"Solving Quantified Modal Logic Problems by Translation to Classical Logics","date":"2022-12-19","arxiv_id":"2212.09570","repositories_listed":1,"syntology":null},{"url":"/paper/peano-learning-formal-mathematical-reasoning","slug":"peano-learning-formal-mathematical-reasoning","title":"Peano: Learning Formal Mathematical Reasoning","date":"2022-11-29","arxiv_id":"2211.15864","repositories_listed":1,"syntology":null},{"url":"/paper/naturalprover-grounded-mathematical-proof","slug":"naturalprover-grounded-mathematical-proof","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","date":"2022-05-25","arxiv_id":"2205.12910","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/naturalprover-grounded-mathematical-proof#ran","syntology_url":"https://syntology.ai/paper/2205.12910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12910"}},"official":{"repos":["wellecks/naturalprover"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-isabelle-enigma","slug":"the-isabelle-enigma","title":"The Isabelle ENIGMA","date":"2022-05-04","arxiv_id":"2205.01981","repositories_listed":1,"syntology":null},{"url":"/paper/logically-consistent-adversarial-attacks-for","slug":"logically-consistent-adversarial-attacks-for","title":"Logically Consistent Adversarial Attacks for Soft Theorem Provers","date":"2022-04-29","arxiv_id":"2205.00047","repositories_listed":1,"syntology":null},{"url":"/paper/the-proof-is-in-the-pudding-using-automated","slug":"the-proof-is-in-the-pudding-using-automated","title":"The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes","date":"2022-03-05","arxiv_id":"2203.02683","repositories_listed":1,"syntology":null},{"url":"/paper/formal-mathematics-statement-curriculum","slug":"formal-mathematics-statement-curriculum","title":"Formal Mathematics Statement Curriculum Learning","date":"2022-02-03","arxiv_id":"2202.01344","repositories_listed":1,"syntology":null},{"url":"/paper/an-energy-based-model-for-neuro-symbolic","slug":"an-energy-based-model-for-neuro-symbolic","title":"An energy-based model for neuro-symbolic reasoning on knowledge graphs","date":"2021-10-04","arxiv_id":"2110.01639","repositories_listed":1,"syntology":null},{"url":"/paper/neural-unification-for-logic-reasoning-over","slug":"neural-unification-for-logic-reasoning-over","title":"Neural Unification for Logic Reasoning over Natural Language","date":"2021-09-17","arxiv_id":"2109.08460","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/neural-unification-for-logic-reasoning-over#ran","syntology_url":"https://syntology.ai/paper/2109.08460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08460"}},"official":{"repos":["ibm/neural_unification_for_logic_reasoning_over_language"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/integration-of-data-and-theory-for","slug":"integration-of-data-and-theory-for","title":"AI Descartes: Combining Data and Theory for Derivable Scientific Discovery","date":"2021-09-03","arxiv_id":"2109.01634","repositories_listed":1,"syntology":null},{"url":"/paper/proofver-natural-logic-theorem-proving-for","slug":"proofver-natural-logic-theorem-proving-for","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","date":"2021-08-25","arxiv_id":"2108.11357","repositories_listed":1,"syntology":null},{"url":"/paper/learning-theorem-proving-components","slug":"learning-theorem-proving-components","title":"Learning Theorem Proving Components","date":"2021-07-21","arxiv_id":"2107.10034","repositories_listed":1,"syntology":null},{"url":"/paper/naturalproofs-mathematical-theorem-proving-in","slug":"naturalproofs-mathematical-theorem-proving-in","title":"NaturalProofs: Mathematical Theorem Proving in Natural Language","date":"2021-03-24","arxiv_id":"2104.01112","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/naturalproofs-mathematical-theorem-proving-in#ran","syntology_url":"https://syntology.ai/paper/2104.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01112"}},"official":{"repos":["wellecks/naturalproofs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-as-abduction-trainable-natural-logic","slug":"learning-as-abduction-trainable-natural-logic","title":"Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference","date":"2020-10-29","arxiv_id":"2010.15909","repositories_listed":1,"syntology":null},{"url":"/paper/int-an-inequality-benchmark-for-evaluating","slug":"int-an-inequality-benchmark-for-evaluating","title":"INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving","date":"2020-07-06","arxiv_id":"2007.02924","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/int-an-inequality-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2007.02924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02924"}},"official":{"repos":["albertqjiang/INT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/logical-inferences-with-comparatives-and","slug":"logical-inferences-with-comparatives-and","title":"Logical Inferences with Comparatives and Generalized Quantifiers","date":"2020-05-16","arxiv_id":"2005.07954","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 3 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/logical-inferences-with-comparatives-and#ran","syntology_url":"https://syntology.ai/paper/2005.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.07954"}},"official":{"repos":["izumi-h/ccgcomp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prolog-technology-reinforcement-learning","slug":"prolog-technology-reinforcement-learning","title":"Prolog Technology Reinforcement Learning Prover","date":"2020-04-15","arxiv_id":"2004.06997","repositories_listed":1,"syntology":null},{"url":"/paper/oxkbc-outcome-explanation-for-factorization","slug":"oxkbc-outcome-explanation-for-factorization","title":"OxKBC: Outcome Explanation for Factorization Based Knowledge Base Completion","date":"2020-02-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-graph-neural-network","slug":"improving-graph-neural-network","title":"Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling","date":"2019-11-15","arxiv_id":"1911.06904","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improving-graph-neural-network#ran","syntology_url":"https://syntology.ai/paper/1911.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06904"}},"official":null}},{"url":"/paper/aplib-tactical-programming-of-intelligent","slug":"aplib-tactical-programming-of-intelligent","title":"Aplib: Tactical Programming of Intelligent Agents","date":"2019-11-12","arxiv_id":"1911.04710","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-reinforcement-learning-based-approach","slug":"a-deep-reinforcement-learning-based-approach","title":"A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving","date":"2019-11-05","arxiv_id":"1911.02065","repositories_listed":1,"syntology":null},{"url":"/paper/g2sat-learning-to-generate-sat-formulas","slug":"g2sat-learning-to-generate-sat-formulas","title":"G2SAT: Learning to Generate SAT Formulas","date":"2019-10-29","arxiv_id":"1910.13445","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/g2sat-learning-to-generate-sat-formulas#ran","syntology_url":"https://syntology.ai/paper/1910.13445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13445"}},"official":null}},{"url":"/paper/deep-reinforcement-learning-in-hol4","slug":"deep-reinforcement-learning-in-hol4","title":"Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic","date":"2019-10-25","arxiv_id":"1910.11797","repositories_listed":1,"syntology":null},{"url":"/paper/neural-theorem-provers-do-not-learn-rules","slug":"neural-theorem-provers-do-not-learn-rules","title":"Neural Theorem Provers Do Not Learn Rules Without Exploration","date":"2019-06-17","arxiv_id":"1906.06805","repositories_listed":1,"syntology":null},{"url":"/paper/towards-finding-longer-proofs","slug":"towards-finding-longer-proofs","title":"Towards Finding Longer Proofs","date":"2019-05-30","arxiv_id":"1905.13100","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-prove-theorems-via-interacting","slug":"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}],"syntology_records":44,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":3,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","since_archive":"/sota/automated-theorem-proving-on-minif2f-test#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-valid","since_archive":"/sota/automated-theorem-proving-on-minif2f-valid#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":46,"papers_where_code_ran_first_page":"/task/automated-theorem-proving/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/automated-theorem-proving/papers/2","json":"/task/automated-theorem-proving/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/automated-theorem-proving/papers/3","json":"/task/automated-theorem-proving/papers/3.json","rows":88},{"order":"ran","page":1,"of":1,"url":"/task/automated-theorem-proving/papers/ran/1","json":"/task/automated-theorem-proving/papers/ran/1.json","rows":46}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"b45aca9e1f3ab4becd4449d9bd98f24bdb750a70e96fa04702d0a75578f50757","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}