{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W6IWLF6EHUWDOZ6N7UBJW2SD3P","short_pith_number":"pith:W6IWLF6E","schema_version":"1.0","canonical_sha256":"b7916597c43d2c3767cdfd029b6a43dbc5403da8eaef29589ebe0af524615121","source":{"kind":"arxiv","id":"2605.22763","version":1},"attestation_state":"computed","paper":{"title":"Advancing Mathematics Research with AI-Driven Formal Proof Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Zsolt Wagner, Aja Huang, Andrew Ferrauiolo, Anja Surina, Anton Kovsharov, Arun Suggala, Codrut Grosu, Eric Wieser, Francisco J. R. Ruiz, George Tsoukalas, Gergely B\\'erczi, Henryk Michalewski, Lei Yu, Matej Balog, Mikl\\'os Z. Horv\\'ath, Moritz Firsching, Pushmeet Kohli, Sergey Shirobokov, Swarat Chaudhuri, Thomas Hubert","submitted_at":"2026-05-21T17:24:57Z","abstract_excerpt":"Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research. A mitigation is using LLMs to generate formal proofs in languages like Lean. We perform the first large-scale evaluation of this method's ability to solve open problems. Our most capable agent autonomously resolved 9 of 353 open Erd\\H{o}s problems at the per-problem cost of a few hundred dollars, proved 44/492 OEIS conjectures, and is being deployed in combinatorics, optimization, graph theory, algebraic geometry, and quantum optics research. A basic "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.22763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T17:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"d1f9e3501f2023491093049a2ef441158b3f925f8a81c534086851d6060401de","abstract_canon_sha256":"c3fb98728d390ff5c996b61f32590a82b8ec932b0ba9338cf112c3c25928d3bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:53.969010Z","signature_b64":"E0Mm02g1Xudshz1/FZuEwM617wPtIOkaUpJjdkOIsFnSfQtpRbfZYBWRyTAgnEOP72gQs5gG+iiAdFUFaKlfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7916597c43d2c3767cdfd029b6a43dbc5403da8eaef29589ebe0af524615121","last_reissued_at":"2026-05-22T02:04:53.968516Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:53.968516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Mathematics Research with AI-Driven Formal Proof Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Zsolt Wagner, Aja Huang, Andrew Ferrauiolo, Anja Surina, Anton Kovsharov, Arun Suggala, Codrut Grosu, Eric Wieser, Francisco J. R. Ruiz, George Tsoukalas, Gergely B\\'erczi, Henryk Michalewski, Lei Yu, Matej Balog, Mikl\\'os Z. Horv\\'ath, Moritz Firsching, Pushmeet Kohli, Sergey Shirobokov, Swarat Chaudhuri, Thomas Hubert","submitted_at":"2026-05-21T17:24:57Z","abstract_excerpt":"Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research. A mitigation is using LLMs to generate formal proofs in languages like Lean. We perform the first large-scale evaluation of this method's ability to solve open problems. Our most capable agent autonomously resolved 9 of 353 open Erd\\H{o}s problems at the per-problem cost of a few hundred dollars, proved 44/492 OEIS conjectures, and is being deployed in combinatorics, optimization, graph theory, algebraic geometry, and quantum optics research. A basic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22763","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.22763/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.22763","created_at":"2026-05-22T02:04:53.968593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22763v1","created_at":"2026-05-22T02:04:53.968593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22763","created_at":"2026-05-22T02:04:53.968593+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6IWLF6EHUWD","created_at":"2026-05-22T02:04:53.968593+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6IWLF6EHUWDOZ6N","created_at":"2026-05-22T02:04:53.968593+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6IWLF6E","created_at":"2026-05-22T02:04:53.968593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P","json":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P.json","graph_json":"https://pith.science/api/pith-number/W6IWLF6EHUWDOZ6N7UBJW2SD3P/graph.json","events_json":"https://pith.science/api/pith-number/W6IWLF6EHUWDOZ6N7UBJW2SD3P/events.json","paper":"https://pith.science/paper/W6IWLF6E"},"agent_actions":{"view_html":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P","download_json":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P.json","view_paper":"https://pith.science/paper/W6IWLF6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22763&json=true","fetch_graph":"https://pith.science/api/pith-number/W6IWLF6EHUWDOZ6N7UBJW2SD3P/graph.json","fetch_events":"https://pith.science/api/pith-number/W6IWLF6EHUWDOZ6N7UBJW2SD3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P/action/storage_attestation","attest_author":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P/action/author_attestation","sign_citation":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P/action/citation_signature","submit_replication":"https://pith.science/pith/W6IWLF6EHUWDOZ6N7UBJW2SD3P/action/replication_record"}},"created_at":"2026-05-22T02:04:53.968593+00:00","updated_at":"2026-05-22T02:04:53.968593+00:00"}