{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MNRQKZPQ2PHCRYIRA4VO7BUIPL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7a8d435038577fc07739f1663e7d1bdac97a221c0083b217d00cdfeffe03a040","cross_cats_sorted":["cs.CL","cs.LG","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T19:16:54Z","title_canon_sha256":"5678ce9e5e3c8568ccefced5bc7d2b5ca26cfb97579b55b0b15f595f9ad1bd46"},"schema_version":"1.0","source":{"id":"2502.15795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15795","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15795v1","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15795","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"MNRQKZPQ2PHC","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"MNRQKZPQ2PHCRYIR","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"MNRQKZPQ","created_at":"2026-07-05T10:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:0664ebb7beb88939e5fb1bda343340e9ae1c2f4a1a3f44856cb780108a2269a7","target":"graph","created_at":"2026-07-05T10:18:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.15795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoformalization, the process of transforming informal mathematical language into formal specifications and proofs remains a difficult task for state-of-the-art (large) language models. Existing works point to competing explanations for the performance gap. To this end, we introduce a novel methodology that leverages back-translation with hand-curated prompts to enhance the mathematical capabilities of language models, particularly addressing the challenge posed by the scarcity of labeled data. Specifically, we evaluate three primary variations of this strategy: (1) on-the-fly (online) backtr","authors_text":"Brando Miranda, Elyas Obbad, Jakob Nordhagen, Kai Fronsdal Sanmi Koyejo, Michael Souliman, Willy Chan","cross_cats":["cs.CL","cs.LG","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T19:16:54Z","title":"Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15795","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:34eb660083207e3d42f7b4a7e1412d2af2583397f5571e6c922f84857e6599e2","target":"record","created_at":"2026-07-05T10:18:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7a8d435038577fc07739f1663e7d1bdac97a221c0083b217d00cdfeffe03a040","cross_cats_sorted":["cs.CL","cs.LG","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T19:16:54Z","title_canon_sha256":"5678ce9e5e3c8568ccefced5bc7d2b5ca26cfb97579b55b0b15f595f9ad1bd46"},"schema_version":"1.0","source":{"id":"2502.15795","kind":"arxiv","version":1}},"canonical_sha256":"63630565f0d3ce28e111072aef86887af29b7a884fe14c8988e6dcae44724440","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63630565f0d3ce28e111072aef86887af29b7a884fe14c8988e6dcae44724440","first_computed_at":"2026-07-05T10:18:16.467391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:16.467391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3mUHfC6s8NncE82HpfJKB7qsE9TdfxGsmmrc/Ne36xJBvAaysQKHVSIqG3HHU1Bow3Y3FOzatxS/bQYeP5w8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:16.467820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34eb660083207e3d42f7b4a7e1412d2af2583397f5571e6c922f84857e6599e2","sha256:0664ebb7beb88939e5fb1bda343340e9ae1c2f4a1a3f44856cb780108a2269a7"],"state_sha256":"6472aa1876a3897ff63dbde0b36e1382ef294c4c54bc3095b5b0b884f7237dc9"}