{"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":"/paper/hypertree-proof-search-for-neural-theorem","title":"HyperTree Proof Search for Neural Theorem Proving","arxiv_id":"2205.11491","date":"2022-05-23","proceeding":null,"authors":["Guillaume Lample","Marie-Anne Lachaux","Thibaut Lavril","Xavier Martinet","Amaury Hayat","Gabriel Ebner","Aurélien Rodriguez","Timothée Lacroix"],"abstract":"We propose an online training procedure for a transformer-based automated theorem prover. Our approach leverages a new search algorithm, HyperTree Proof Search (HTPS), inspired by the recent success of AlphaZero. Our model learns from previous proof searches through online training, allowing it to generalize to domains far from the training distribution. We report detailed ablations of our pipeline's main components by studying performance on three environments of increasing complexity. In particular, we show that with HTPS alone, a model trained on annotated proofs manages to prove 65.4% of a held-out set of Metamath theorems, significantly outperforming the previous state of the art of 56.5% by GPT-f. Online training on these unproved theorems increases accuracy to 82.6%. With a similar computational budget, we improve the state of the art on the Lean-based miniF2F-curriculum dataset from 31% to 42% proving accuracy.","url_abs":"https://arxiv.org/abs/2205.11491v1","url_pdf":"https://arxiv.org/pdf/2205.11491v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"}],"methods":[{"method_slug":"alphazero","method_name":"AlphaZero"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/automated-theorem-proving-on-metamath-setmm","task":"Automated Theorem Proving","dataset":"Metamath set.mm","model":"Evariste","rank_in_archive_order":4,"of":4,"metrics":{"Pass@32":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-1","task":"Automated Theorem Proving","dataset":"miniF2F-curriculum","model":"Evariste-7d","rank_in_archive_order":1,"of":4,"metrics":{"Pass@64":"42.5"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-1","task":"Automated Theorem Proving","dataset":"miniF2F-curriculum","model":"Evariste-1d","rank_in_archive_order":2,"of":4,"metrics":{"Pass@64":"33.6"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-1","task":"Automated Theorem Proving","dataset":"miniF2F-curriculum","model":"Evariste","rank_in_archive_order":3,"of":4,"metrics":{"Pass@64":"32.1"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-1","task":"Automated Theorem Proving","dataset":"miniF2F-curriculum","model":"GPT-f","rank_in_archive_order":4,"of":4,"metrics":{"Pass@64":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"Evariste","rank_in_archive_order":9,"of":29,"metrics":{"ITP":"Lean","Pass@64":"41","cumulative":"41"},"uses_additional_data":true},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"Evariste-7d","rank_in_archive_order":10,"of":29,"metrics":{"ITP":"Lean","Pass@64":"40.6","cumulative":"40.6"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"Evariste-1d","rank_in_archive_order":11,"of":29,"metrics":{"ITP":"Lean","Pass@64":"38.9","cumulative":"38.9"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"GPT-f","rank_in_archive_order":14,"of":29,"metrics":{"ITP":"Metamath","Pass@64":"36.6","cumulative":"36.6"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-valid","task":"Automated Theorem Proving","dataset":"miniF2F-valid","model":"Evariste","rank_in_archive_order":3,"of":10,"metrics":{"Pass@64":"58.6"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-valid","task":"Automated Theorem Proving","dataset":"miniF2F-valid","model":"Evariste-7d","rank_in_archive_order":4,"of":10,"metrics":{"Pass@64":"47.5"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-valid","task":"Automated Theorem Proving","dataset":"miniF2F-valid","model":"GPT-f","rank_in_archive_order":5,"of":10,"metrics":{"Pass@64":"47.3"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-valid","task":"Automated Theorem Proving","dataset":"miniF2F-valid","model":"Evariste-1d","rank_in_archive_order":6,"of":10,"metrics":{"Pass@64":"46.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.11491","atlas_url":"https://app.syntology.ai/?focus=2205.11491","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2205.11491"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.11491\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.11491"},"call":"get_concepts_for_paper(arxiv_id=\"2205.11491\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e5b2b7b56ef27ae7f21b28a381f5dff5cb627677119a3033056620ec5170b3bd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}