{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:44TYLDSL4T3TSIEBATL5Q6RUTX","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":"f2054f8ccdca06462f87e487cbf24b7a11fa5ca7c114ff1d5ddbb71932440806","cross_cats_sorted":["cs.AI","cs.LG","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:11:24Z","title_canon_sha256":"fb2d380c6215367dff0a66eb8911cc3a3f7588fc2ce294804337179e2961bc52"},"schema_version":"1.0","source":{"id":"2410.10878","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10878","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10878v2","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10878","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"44TYLDSL4T3T","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"44TYLDSL4T3TSIEB","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"44TYLDSL","created_at":"2026-07-05T10:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:15a8d713f7d07107ea6a0a5b9699c057b27ed292410d3bf33ae150cc890b68b7","target":"graph","created_at":"2026-07-05T10:20:40Z","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/2410.10878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Verifiable formal languages like Lean have profoundly impacted mathematical reasoning, particularly through the use of large language models (LLMs) for automated reasoning. A significant challenge in training LLMs for these formal languages is the lack of parallel datasets that align natural language with formal language proofs. To address this challenge, this paper introduces a novel framework for translating the Mathlib4 corpus (a unified library of mathematics in formal language Lean 4) into natural language. Building upon this, we employ a dual augmentation strategy that combines tactic-ba","authors_text":"Bin Dong, Guoxiong Gao, Jiedong Jiang, Qi Gao, Tianyi Xu, Yutong Wang, Zihan Qin","cross_cats":["cs.AI","cs.LG","cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:11:24Z","title":"Herald: A Natural Language Annotated Lean 4 Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10878","kind":"arxiv","version":2},"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":"sha256:790ef40d57179cf46e6b26c1caac2f1ed5d9d741362dec66d8eb743742b06625","target":"record","created_at":"2026-07-05T10:20:40Z","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":"f2054f8ccdca06462f87e487cbf24b7a11fa5ca7c114ff1d5ddbb71932440806","cross_cats_sorted":["cs.AI","cs.LG","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:11:24Z","title_canon_sha256":"fb2d380c6215367dff0a66eb8911cc3a3f7588fc2ce294804337179e2961bc52"},"schema_version":"1.0","source":{"id":"2410.10878","kind":"arxiv","version":2}},"canonical_sha256":"e727858e4be4f739208104d7d87a349dc87bd37999fc5090224a67782bb173c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e727858e4be4f739208104d7d87a349dc87bd37999fc5090224a67782bb173c1","first_computed_at":"2026-07-05T10:20:40.626743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:40.626743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aIx/J/qnwnFdSB8UAy8hITVmGqU/Gq2RntHWuukH04d79zP/k9mlbIKu3ucjwpZL7QfqgphgmktnNdSw6ufpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:40.627367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10878","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:790ef40d57179cf46e6b26c1caac2f1ed5d9d741362dec66d8eb743742b06625","sha256:15a8d713f7d07107ea6a0a5b9699c057b27ed292410d3bf33ae150cc890b68b7"],"state_sha256":"af6b9a41350d004f6cc41e945b9908f08f3aaebb84d822162ada236d22a89698"}