{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QB6XWXA7DHSHC2BBKN3CZMGUFR","short_pith_number":"pith:QB6XWXA7","schema_version":"1.0","canonical_sha256":"807d7b5c1f19e471682153762cb0d42c7f0c0713e2fabed964e5dc76418ee73b","source":{"kind":"arxiv","id":"2410.20936","version":2},"attestation_state":"computed","paper":{"title":"Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Yang, Xian Zhang, Xiaoxing Ma, Xinming Wei, Yifan Wu, Zenan Li, Zhaoyu Li","submitted_at":"2024-10-28T11:37:39Z","abstract_excerpt":"Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models (LLMs) have unveiled their promising capabilities to formalize even competition-level math problems. However, we observe a considerable discrepancy between pass@1 and pass@k accuracies in LLM-generated formalizations. To address this gap, we introduce a novel framework that scores and selects the best result from k autoformalization candidates based on two comp"},"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":"2410.20936","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T11:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"5a430fcbb4b85e17faa4b403da34e2bf2a0503f9b8240fce047e941507291519","abstract_canon_sha256":"499afd8d1d55cda950058c4d75b7cc26c94695b4ba61343c6ee5a377a14e4a89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:15.830557Z","signature_b64":"H07TrdnGjJRwg8h8z/xsZfaIQCqzCnOIH2zYtX8usIE/xHebuDYB8vo+hzTzgF2w3EOgASfJpswoNxsFuOoTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"807d7b5c1f19e471682153762cb0d42c7f0c0713e2fabed964e5dc76418ee73b","last_reissued_at":"2026-07-05T09:45:15.830069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:15.830069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Yang, Xian Zhang, Xiaoxing Ma, Xinming Wei, Yifan Wu, Zenan Li, Zhaoyu Li","submitted_at":"2024-10-28T11:37:39Z","abstract_excerpt":"Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models (LLMs) have unveiled their promising capabilities to formalize even competition-level math problems. However, we observe a considerable discrepancy between pass@1 and pass@k accuracies in LLM-generated formalizations. To address this gap, we introduce a novel framework that scores and selects the best result from k autoformalization candidates based on two comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20936","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/2410.20936/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":"2410.20936","created_at":"2026-07-05T09:45:15.830123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20936v2","created_at":"2026-07-05T09:45:15.830123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20936","created_at":"2026-07-05T09:45:15.830123+00:00"},{"alias_kind":"pith_short_12","alias_value":"QB6XWXA7DHSH","created_at":"2026-07-05T09:45:15.830123+00:00"},{"alias_kind":"pith_short_16","alias_value":"QB6XWXA7DHSHC2BB","created_at":"2026-07-05T09:45:15.830123+00:00"},{"alias_kind":"pith_short_8","alias_value":"QB6XWXA7","created_at":"2026-07-05T09:45:15.830123+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/QB6XWXA7DHSHC2BBKN3CZMGUFR","json":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR.json","graph_json":"https://pith.science/api/pith-number/QB6XWXA7DHSHC2BBKN3CZMGUFR/graph.json","events_json":"https://pith.science/api/pith-number/QB6XWXA7DHSHC2BBKN3CZMGUFR/events.json","paper":"https://pith.science/paper/QB6XWXA7"},"agent_actions":{"view_html":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR","download_json":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR.json","view_paper":"https://pith.science/paper/QB6XWXA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20936&json=true","fetch_graph":"https://pith.science/api/pith-number/QB6XWXA7DHSHC2BBKN3CZMGUFR/graph.json","fetch_events":"https://pith.science/api/pith-number/QB6XWXA7DHSHC2BBKN3CZMGUFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR/action/storage_attestation","attest_author":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR/action/author_attestation","sign_citation":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR/action/citation_signature","submit_replication":"https://pith.science/pith/QB6XWXA7DHSHC2BBKN3CZMGUFR/action/replication_record"}},"created_at":"2026-07-05T09:45:15.830123+00:00","updated_at":"2026-07-05T09:45:15.830123+00:00"}