{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ISM7HZHSTD6DA57SVGMDDPUVLM","short_pith_number":"pith:ISM7HZHS","schema_version":"1.0","canonical_sha256":"4499f3e4f298fc3077f2a99831be955b3a63698e109324a4b80d9b14d1dfb3ee","source":{"kind":"arxiv","id":"2505.22451","version":1},"attestation_state":"computed","paper":{"title":"AI Mathematician: Towards Fully Automated Frontier Mathematical Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peng Li, Yang Liu, Yanqiao Wang, Yanxing Huang, Yuanhang Liu","submitted_at":"2025-05-28T15:10:37Z","abstract_excerpt":"Large Reasoning Models (LRMs) have made significant progress in mathematical capabilities in recent times. However, these successes have been primarily confined to competition-level problems. In this work, we propose AI Mathematician (AIM) framework, which harnesses the reasoning strength of LRMs to support frontier mathematical research. We have identified two critical challenges of mathematical research compared to competition, {\\it the intrinsic complexity of research problems} and {\\it the requirement of procedural rigor}. To address these challenges, AIM incorporates two core strategies: "},"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":"2505.22451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-28T15:10:37Z","cross_cats_sorted":[],"title_canon_sha256":"a1982a453c62cd763945d00bfbc94ebd0dd5207218cc682ff54b39a66a985ac4","abstract_canon_sha256":"768449c687569f49625aaaa30d426847d7c787ebbec41c559ef707afd9961c76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:24.313993Z","signature_b64":"ABkdvrkvjnUX9nDO3JsWrrswKNjUuBrqWQUwHFUwEsoGo2Sja6bMgcYi9miJ0DMwdEz9TJuxB0wiHB7qnFAfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4499f3e4f298fc3077f2a99831be955b3a63698e109324a4b80d9b14d1dfb3ee","last_reissued_at":"2026-07-05T11:11:24.313337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:24.313337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Mathematician: Towards Fully Automated Frontier Mathematical Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peng Li, Yang Liu, Yanqiao Wang, Yanxing Huang, Yuanhang Liu","submitted_at":"2025-05-28T15:10:37Z","abstract_excerpt":"Large Reasoning Models (LRMs) have made significant progress in mathematical capabilities in recent times. However, these successes have been primarily confined to competition-level problems. In this work, we propose AI Mathematician (AIM) framework, which harnesses the reasoning strength of LRMs to support frontier mathematical research. We have identified two critical challenges of mathematical research compared to competition, {\\it the intrinsic complexity of research problems} and {\\it the requirement of procedural rigor}. To address these challenges, AIM incorporates two core strategies: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22451","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/2505.22451/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":"2505.22451","created_at":"2026-07-05T11:11:24.313414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22451v1","created_at":"2026-07-05T11:11:24.313414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22451","created_at":"2026-07-05T11:11:24.313414+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISM7HZHSTD6D","created_at":"2026-07-05T11:11:24.313414+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISM7HZHSTD6DA57S","created_at":"2026-07-05T11:11:24.313414+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISM7HZHS","created_at":"2026-07-05T11:11:24.313414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24899","citing_title":"From Meta Idea to Advanced Mathematical Discovery -- Human-AI Co-Discovery of Sign-Embedding Quantum Algorithms","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25333","citing_title":"Sign Embedding Quantum Algorithms for Matrix Equations and Matrix Functions","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM","json":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM.json","graph_json":"https://pith.science/api/pith-number/ISM7HZHSTD6DA57SVGMDDPUVLM/graph.json","events_json":"https://pith.science/api/pith-number/ISM7HZHSTD6DA57SVGMDDPUVLM/events.json","paper":"https://pith.science/paper/ISM7HZHS"},"agent_actions":{"view_html":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM","download_json":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM.json","view_paper":"https://pith.science/paper/ISM7HZHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22451&json=true","fetch_graph":"https://pith.science/api/pith-number/ISM7HZHSTD6DA57SVGMDDPUVLM/graph.json","fetch_events":"https://pith.science/api/pith-number/ISM7HZHSTD6DA57SVGMDDPUVLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM/action/storage_attestation","attest_author":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM/action/author_attestation","sign_citation":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM/action/citation_signature","submit_replication":"https://pith.science/pith/ISM7HZHSTD6DA57SVGMDDPUVLM/action/replication_record"}},"created_at":"2026-07-05T11:11:24.313414+00:00","updated_at":"2026-07-05T11:11:24.313414+00:00"}