{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XPPI7V4AKHBPRDBIFVPISPTIJ3","short_pith_number":"pith:XPPI7V4A","schema_version":"1.0","canonical_sha256":"bbde8fd78051c2f88c282d5e893e684edb2cb9daed99e597900e0d1c198fb865","source":{"kind":"arxiv","id":"2606.09449","version":1},"attestation_state":"computed","paper":{"title":"Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e Freitas, Lei Xu, Xin Quan","submitted_at":"2026-06-08T12:57:09Z","abstract_excerpt":"Complex reasoning tasks increasingly require systems to produce outputs whose correctness cannot be judged by exact match against a single reference. Autoformalization (AF) is a representative example; it asks a model to translate informal mathematical or logical reasoning into a formally checkable object, yet expert-validated formalizations do not scale beyond toy cases and a single informal argument can admit many valid formal renderings. Progress therefore depends on whether partial, structured proxies can substitute for exact references.\n  We introduce a reference-free proxy-judge framewor"},"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":"2606.09449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"2cfc168d3cace15e316d43cba83aa7370f3a0b87337bac1ba7ab6e2dde3e98d2","abstract_canon_sha256":"f435c7db005ccebd1448aa0a9993a18252442b84cec45e7edebaf11dc7255b21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:49.200747Z","signature_b64":"IUr0CyN4LAZwpAwm8BApzlkjQexgIOC3U0Hho8RNE+ynclkOEvms3Cwc21roLQRe49RGxAZ7jfya5Y7ND+XVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbde8fd78051c2f88c282d5e893e684edb2cb9daed99e597900e0d1c198fb865","last_reissued_at":"2026-06-09T02:08:49.199907Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:49.199907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e Freitas, Lei Xu, Xin Quan","submitted_at":"2026-06-08T12:57:09Z","abstract_excerpt":"Complex reasoning tasks increasingly require systems to produce outputs whose correctness cannot be judged by exact match against a single reference. Autoformalization (AF) is a representative example; it asks a model to translate informal mathematical or logical reasoning into a formally checkable object, yet expert-validated formalizations do not scale beyond toy cases and a single informal argument can admit many valid formal renderings. Progress therefore depends on whether partial, structured proxies can substitute for exact references.\n  We introduce a reference-free proxy-judge framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09449","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/2606.09449/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":"2606.09449","created_at":"2026-06-09T02:08:49.200044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09449v1","created_at":"2026-06-09T02:08:49.200044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09449","created_at":"2026-06-09T02:08:49.200044+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPPI7V4AKHBP","created_at":"2026-06-09T02:08:49.200044+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPPI7V4AKHBPRDBI","created_at":"2026-06-09T02:08:49.200044+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPPI7V4A","created_at":"2026-06-09T02:08:49.200044+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/XPPI7V4AKHBPRDBIFVPISPTIJ3","json":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3.json","graph_json":"https://pith.science/api/pith-number/XPPI7V4AKHBPRDBIFVPISPTIJ3/graph.json","events_json":"https://pith.science/api/pith-number/XPPI7V4AKHBPRDBIFVPISPTIJ3/events.json","paper":"https://pith.science/paper/XPPI7V4A"},"agent_actions":{"view_html":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3","download_json":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3.json","view_paper":"https://pith.science/paper/XPPI7V4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09449&json=true","fetch_graph":"https://pith.science/api/pith-number/XPPI7V4AKHBPRDBIFVPISPTIJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/XPPI7V4AKHBPRDBIFVPISPTIJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3/action/storage_attestation","attest_author":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3/action/author_attestation","sign_citation":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3/action/citation_signature","submit_replication":"https://pith.science/pith/XPPI7V4AKHBPRDBIFVPISPTIJ3/action/replication_record"}},"created_at":"2026-06-09T02:08:49.200044+00:00","updated_at":"2026-06-09T02:08:49.200044+00:00"}