{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PZBEA2OBXFGGB5NEYNJ26BOK6I","short_pith_number":"pith:PZBEA2OB","schema_version":"1.0","canonical_sha256":"7e424069c1b94c60f5a4c353af05caf20603da89b367c3c84c1bad98813e62ac","source":{"kind":"arxiv","id":"2507.06804","version":1},"attestation_state":"computed","paper":{"title":"Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LO","authors_text":"Dong Yu, Feng Zhang, Haitao Mi, Linfeng Song, Tao Yang, Yang Li, Zhenwen Liang","submitted_at":"2025-07-07T22:38:49Z","abstract_excerpt":"Automated Theorem Proving (ATP) in formal languages is a foundational challenge for AI. While Large Language Models (LLMs) have driven remarkable progress, a significant gap remains between their powerful informal reasoning capabilities and their weak formal proving performance. Recent studies show that the informal accuracy exceeds 80% while formal success remains below 8% on benchmarks like PutnamBench. We argue this gap persists because current state-of-the-art provers, by tightly coupling reasoning and proving, are trained with paradigms that inadvertently punish deep reasoning in favor of"},"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":"2507.06804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2025-07-07T22:38:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7286b608a1a7312c2cffc29c14231b50a0e1f6eb5e0d4a96efe2326e5d0d581","abstract_canon_sha256":"225b9f3e00e1cf822bb2397a095f46c725dcd3f68f3546ad11b0c90b6e362231"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:23.293717Z","signature_b64":"w2gkaFZ5f2bZpt67qAU4OPKAYYts6bDEXjvbfB/ASAddZCHIr2RAt1YhJ9mJcp51rA4mUePW4mTSr+u9kLbCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e424069c1b94c60f5a4c353af05caf20603da89b367c3c84c1bad98813e62ac","last_reissued_at":"2026-07-05T11:34:23.293232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:23.293232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LO","authors_text":"Dong Yu, Feng Zhang, Haitao Mi, Linfeng Song, Tao Yang, Yang Li, Zhenwen Liang","submitted_at":"2025-07-07T22:38:49Z","abstract_excerpt":"Automated Theorem Proving (ATP) in formal languages is a foundational challenge for AI. While Large Language Models (LLMs) have driven remarkable progress, a significant gap remains between their powerful informal reasoning capabilities and their weak formal proving performance. Recent studies show that the informal accuracy exceeds 80% while formal success remains below 8% on benchmarks like PutnamBench. We argue this gap persists because current state-of-the-art provers, by tightly coupling reasoning and proving, are trained with paradigms that inadvertently punish deep reasoning in favor of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06804","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/2507.06804/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":"2507.06804","created_at":"2026-07-05T11:34:23.293290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06804v1","created_at":"2026-07-05T11:34:23.293290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06804","created_at":"2026-07-05T11:34:23.293290+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZBEA2OBXFGG","created_at":"2026-07-05T11:34:23.293290+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZBEA2OBXFGGB5NE","created_at":"2026-07-05T11:34:23.293290+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZBEA2OB","created_at":"2026-07-05T11:34:23.293290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":141,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":142,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I","json":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I.json","graph_json":"https://pith.science/api/pith-number/PZBEA2OBXFGGB5NEYNJ26BOK6I/graph.json","events_json":"https://pith.science/api/pith-number/PZBEA2OBXFGGB5NEYNJ26BOK6I/events.json","paper":"https://pith.science/paper/PZBEA2OB"},"agent_actions":{"view_html":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I","download_json":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I.json","view_paper":"https://pith.science/paper/PZBEA2OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06804&json=true","fetch_graph":"https://pith.science/api/pith-number/PZBEA2OBXFGGB5NEYNJ26BOK6I/graph.json","fetch_events":"https://pith.science/api/pith-number/PZBEA2OBXFGGB5NEYNJ26BOK6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I/action/storage_attestation","attest_author":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I/action/author_attestation","sign_citation":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I/action/citation_signature","submit_replication":"https://pith.science/pith/PZBEA2OBXFGGB5NEYNJ26BOK6I/action/replication_record"}},"created_at":"2026-07-05T11:34:23.293290+00:00","updated_at":"2026-07-05T11:34:23.293290+00:00"}