{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OOJIC3MZWOBBSY3CVQ45JBJFIA","short_pith_number":"pith:OOJIC3MZ","canonical_record":{"source":{"id":"2406.03847","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T08:25:43Z","cross_cats_sorted":[],"title_canon_sha256":"21f31e210ca9e9845aa64c8f27d304f455d59861e3a906e6e8a003aa2eed5161","abstract_canon_sha256":"46e486062d70f8a2609009fb4539a71b45c2d7ce8b5e20bbcc9c33c2b175a72e"},"schema_version":"1.0"},"canonical_sha256":"7392816d99b382196362ac39d48525401c1aae2d940fbe17816e304a31268a7d","source":{"kind":"arxiv","id":"2406.03847","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03847","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03847v3","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03847","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"OOJIC3MZWOBB","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"OOJIC3MZWOBBSY3C","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"OOJIC3MZ","created_at":"2026-07-05T11:23:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OOJIC3MZWOBBSY3CVQ45JBJFIA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03847","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T08:25:43Z","cross_cats_sorted":[],"title_canon_sha256":"21f31e210ca9e9845aa64c8f27d304f455d59861e3a906e6e8a003aa2eed5161","abstract_canon_sha256":"46e486062d70f8a2609009fb4539a71b45c2d7ce8b5e20bbcc9c33c2b175a72e"},"schema_version":"1.0"},"canonical_sha256":"7392816d99b382196362ac39d48525401c1aae2d940fbe17816e304a31268a7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:16.356439Z","signature_b64":"ZhKHj9kVGGpoqi2rEmlsfWid7QbxNNi0IMhZaTDUWd1262pu8/qMOClIbbR8uK//AzYoriRfY/Da13KZPMN5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7392816d99b382196362ac39d48525401c1aae2d940fbe17816e304a31268a7d","last_reissued_at":"2026-07-05T11:23:16.355900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:16.355900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03847","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HWGM0Qn4YvTLgqogQnw+aHqKqWjCVysXKkeetoo7W03HlMRDuvCAsVlr1eDlHUTNEr1xQCymPn4Q/qDIIL/MDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:56:47.459259Z"},"content_sha256":"037ef03b5c64ed379a6e2c5efa4b891d942761c0565900f42bd1a977ba684fc7","schema_version":"1.0","event_id":"sha256:037ef03b5c64ed379a6e2c5efa4b891d942761c0565900f42bd1a977ba684fc7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OOJIC3MZWOBBSY3CVQ45JBJFIA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lean Workbook: A large-scale Lean problem set formalized from natural language math problems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Huaiyuan Ying, Kai Chen, Yihan Geng, Zheng Yuan, Zijian Wu","submitted_at":"2024-06-06T08:25:43Z","abstract_excerpt":"Large language models have demonstrated impressive capabilities across various natural language processing tasks, especially in solving mathematical problems. However, large language models are not good at math theorem proving using formal languages like Lean. A significant challenge in this area is the scarcity of training data available in these formal languages. To address this issue, we propose a novel pipeline that iteratively generates and filters synthetic data to translate natural language mathematical problems into Lean 4 statements, and vice versa. Our results indicate that the synth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03847","kind":"arxiv","version":3},"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/2406.03847/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNrC8VdJapI7BW/kUbPAEPjI+wNrf110HmAsU321FeXR5jsKKP3M43q7dS3TAOEKnhTegBfGUyJ0m+OjX2G7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:56:47.459832Z"},"content_sha256":"b32ce699b1ccb507bfe9c5f7091952de07248bb030a6b7ddd7382321fc7111ca","schema_version":"1.0","event_id":"sha256:b32ce699b1ccb507bfe9c5f7091952de07248bb030a6b7ddd7382321fc7111ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA/bundle.json","state_url":"https://pith.science/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T06:56:47Z","links":{"resolver":"https://pith.science/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA","bundle":"https://pith.science/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA/bundle.json","state":"https://pith.science/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOJIC3MZWOBBSY3CVQ45JBJFIA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OOJIC3MZWOBBSY3CVQ45JBJFIA","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":"46e486062d70f8a2609009fb4539a71b45c2d7ce8b5e20bbcc9c33c2b175a72e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T08:25:43Z","title_canon_sha256":"21f31e210ca9e9845aa64c8f27d304f455d59861e3a906e6e8a003aa2eed5161"},"schema_version":"1.0","source":{"id":"2406.03847","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03847","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03847v3","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03847","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"OOJIC3MZWOBB","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"OOJIC3MZWOBBSY3C","created_at":"2026-07-05T11:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"OOJIC3MZ","created_at":"2026-07-05T11:23:16Z"}],"graph_snapshots":[{"event_id":"sha256:b32ce699b1ccb507bfe9c5f7091952de07248bb030a6b7ddd7382321fc7111ca","target":"graph","created_at":"2026-07-05T11:23:16Z","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/2406.03847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have demonstrated impressive capabilities across various natural language processing tasks, especially in solving mathematical problems. However, large language models are not good at math theorem proving using formal languages like Lean. A significant challenge in this area is the scarcity of training data available in these formal languages. To address this issue, we propose a novel pipeline that iteratively generates and filters synthetic data to translate natural language mathematical problems into Lean 4 statements, and vice versa. Our results indicate that the synth","authors_text":"Dahua Lin, Huaiyuan Ying, Kai Chen, Yihan Geng, Zheng Yuan, Zijian Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T08:25:43Z","title":"Lean Workbook: A large-scale Lean problem set formalized from natural language math problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03847","kind":"arxiv","version":3},"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":"sha256:037ef03b5c64ed379a6e2c5efa4b891d942761c0565900f42bd1a977ba684fc7","target":"record","created_at":"2026-07-05T11:23:16Z","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":"46e486062d70f8a2609009fb4539a71b45c2d7ce8b5e20bbcc9c33c2b175a72e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T08:25:43Z","title_canon_sha256":"21f31e210ca9e9845aa64c8f27d304f455d59861e3a906e6e8a003aa2eed5161"},"schema_version":"1.0","source":{"id":"2406.03847","kind":"arxiv","version":3}},"canonical_sha256":"7392816d99b382196362ac39d48525401c1aae2d940fbe17816e304a31268a7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7392816d99b382196362ac39d48525401c1aae2d940fbe17816e304a31268a7d","first_computed_at":"2026-07-05T11:23:16.355900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:16.355900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhKHj9kVGGpoqi2rEmlsfWid7QbxNNi0IMhZaTDUWd1262pu8/qMOClIbbR8uK//AzYoriRfY/Da13KZPMN5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:16.356439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03847","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:037ef03b5c64ed379a6e2c5efa4b891d942761c0565900f42bd1a977ba684fc7","sha256:b32ce699b1ccb507bfe9c5f7091952de07248bb030a6b7ddd7382321fc7111ca"],"state_sha256":"236a2a20718cccfe3de1efc09bd80faba57ba7fd11958ccbb3ad206294ba3e34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o0V9egyRx0wlnmlfoifoW19NUx5cSOucHwDc6sFugv8OWTi21x8vWkt4c8UzZQYD7LCE0DPIFFL93hJX6owWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:56:47.463597Z","bundle_sha256":"48680e2810226c2522dd60ab51b0ab841e7e9e9be16bd6266606044e57d044f8"}}