{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CJBKL6XIAT3PO2PFIBEY6PJPOL","short_pith_number":"pith:CJBKL6XI","schema_version":"1.0","canonical_sha256":"1242a5fae804f6f769e540498f3d2f72f261592b56d1fd8c62be5a1b3696b596","source":{"kind":"arxiv","id":"2510.04520","version":2},"attestation_state":"computed","paper":{"title":"Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Dong, Guoxiong Gao, Hanyu Wang, Ruohan Xie, Xintao Yu, Yutong Wang","submitted_at":"2025-10-06T06:25:11Z","abstract_excerpt":"Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their inability to synthesize new definitions. To tackle these issues, we present Aria (Agent for Retrieval and Iterative Autoformalization), a system for conjecture-level formalization in Lean that emulates human expert reasoning via a two-phase Graph-of-Thought process: recursively decomposing statements into a dependency graph and then constructing formalization"},"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":"2510.04520","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-06T06:25:11Z","cross_cats_sorted":[],"title_canon_sha256":"8f7f9c1b99bd820fb6c315241e83e214e6fd38b88ae46536892d8b8cf365d681","abstract_canon_sha256":"9b6858dfe0da3c950efe5de73887274b35199ba48f5362c976fef2d1b5f162b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:13.456481Z","signature_b64":"OMMqeqSEz1nzyqghG5oXnF9nVCsjgP3TMo8aM5ZeZ0sHJJpj16alK6lA6XPQwqvMa9sGHcCGatkYEXowI7/BDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1242a5fae804f6f769e540498f3d2f72f261592b56d1fd8c62be5a1b3696b596","last_reissued_at":"2026-07-03T01:17:13.455984Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:13.455984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Dong, Guoxiong Gao, Hanyu Wang, Ruohan Xie, Xintao Yu, Yutong Wang","submitted_at":"2025-10-06T06:25:11Z","abstract_excerpt":"Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their inability to synthesize new definitions. To tackle these issues, we present Aria (Agent for Retrieval and Iterative Autoformalization), a system for conjecture-level formalization in Lean that emulates human expert reasoning via a two-phase Graph-of-Thought process: recursively decomposing statements into a dependency graph and then constructing formalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04520","kind":"arxiv","version":2},"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/2510.04520/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":"2510.04520","created_at":"2026-07-03T01:17:13.456038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.04520v2","created_at":"2026-07-03T01:17:13.456038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04520","created_at":"2026-07-03T01:17:13.456038+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJBKL6XIAT3P","created_at":"2026-07-03T01:17:13.456038+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJBKL6XIAT3PO2PF","created_at":"2026-07-03T01:17:13.456038+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJBKL6XI","created_at":"2026-07-03T01:17:13.456038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":143,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14061","citing_title":"MathAtlas: A Benchmark for Autoformalization in the Wild","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03789","citing_title":"Automated Conjecture Resolution with Formal Verification","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL","json":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL.json","graph_json":"https://pith.science/api/pith-number/CJBKL6XIAT3PO2PFIBEY6PJPOL/graph.json","events_json":"https://pith.science/api/pith-number/CJBKL6XIAT3PO2PFIBEY6PJPOL/events.json","paper":"https://pith.science/paper/CJBKL6XI"},"agent_actions":{"view_html":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL","download_json":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL.json","view_paper":"https://pith.science/paper/CJBKL6XI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.04520&json=true","fetch_graph":"https://pith.science/api/pith-number/CJBKL6XIAT3PO2PFIBEY6PJPOL/graph.json","fetch_events":"https://pith.science/api/pith-number/CJBKL6XIAT3PO2PFIBEY6PJPOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL/action/storage_attestation","attest_author":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL/action/author_attestation","sign_citation":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL/action/citation_signature","submit_replication":"https://pith.science/pith/CJBKL6XIAT3PO2PFIBEY6PJPOL/action/replication_record"}},"created_at":"2026-07-03T01:17:13.456038+00:00","updated_at":"2026-07-03T01:17:13.456038+00:00"}