{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NLNIWFFIKTD5O4CBD3B5PFYULY","short_pith_number":"pith:NLNIWFFI","canonical_record":{"source":{"id":"2407.17227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-24T12:28:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d958ca423c1624a4717f07ddf4a742adc235163d2252ed62bb80bd3cf58cc680","abstract_canon_sha256":"d2ec179f36c3f9b806158f494450f9218855788e7fb293f71741eed571d41c9b"},"schema_version":"1.0"},"canonical_sha256":"6ada8b14a854c7d770411ec3d797145e10aaddde2df5ba307f409435e848c430","source":{"kind":"arxiv","id":"2407.17227","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17227","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17227v1","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17227","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"NLNIWFFIKTD5","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"pith_short_16","alias_value":"NLNIWFFIKTD5O4CB","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"pith_short_8","alias_value":"NLNIWFFI","created_at":"2026-07-05T08:48:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NLNIWFFIKTD5O4CBD3B5PFYULY","target":"record","payload":{"canonical_record":{"source":{"id":"2407.17227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-24T12:28:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d958ca423c1624a4717f07ddf4a742adc235163d2252ed62bb80bd3cf58cc680","abstract_canon_sha256":"d2ec179f36c3f9b806158f494450f9218855788e7fb293f71741eed571d41c9b"},"schema_version":"1.0"},"canonical_sha256":"6ada8b14a854c7d770411ec3d797145e10aaddde2df5ba307f409435e848c430","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:04.132884Z","signature_b64":"LdlrB8bWufP4GiOzCexs80PJ+wp9Zz99W+pljJ6VuR+GXy8Gs8H7MxGB4cUUMlsCScIkIAVYEJmz4xkFPxfyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ada8b14a854c7d770411ec3d797145e10aaddde2df5ba307f409435e848c430","last_reissued_at":"2026-07-05T08:48:04.132455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:04.132455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.17227","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKg+rj6V7cXpWtl9s7YOSbfgCHaqy4yI6T0uF63aK1pbSYRHa6YbTtLOEAQBGrmaqEvcBQpdOtk+C/GjRXF1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:27:48.237609Z"},"content_sha256":"999968143bf9de462834b8d375bed65b80fc7dbfb8b344f4f5126273ac977e6f","schema_version":"1.0","event_id":"sha256:999968143bf9de462834b8d375bed65b80fc7dbfb8b344f4f5126273ac977e6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NLNIWFFIKTD5O4CBD3B5PFYULY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dahua Lin, Jiayu Wang, Kai Chen, Zijian Wu","submitted_at":"2024-07-24T12:28:03Z","abstract_excerpt":"Recently, large language models have presented promising results in aiding formal mathematical reasoning. However, their performance is restricted due to the scarcity of formal theorem-proving data, which requires additional effort to be extracted from raw formal language corpora. Meanwhile, a significant amount of human-written formal language corpora remains underutilized. To address this issue, we propose LEAN-GitHub, a dataset consisting of large-scale formal data extracted from almost all Lean 4 repositories on GitHub. After fine-tuning InternLM-math-plus on this dataset, our model achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17227","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/2407.17227/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":"2026-07-05T08:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hNTGP+cPz/l1OBLYaD3IiVqOOGlmjcXuBPAYz+HhIFNUD+WhORadtyzVHWwx7iWK4bZss6ZXAqqAaVsIfxbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:27:48.238118Z"},"content_sha256":"231a6e7b894f4d1d7bab3524b371d47d81a39fcd342fdf44b6fb0a96146bca37","schema_version":"1.0","event_id":"sha256:231a6e7b894f4d1d7bab3524b371d47d81a39fcd342fdf44b6fb0a96146bca37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLNIWFFIKTD5O4CBD3B5PFYULY/bundle.json","state_url":"https://pith.science/pith/NLNIWFFIKTD5O4CBD3B5PFYULY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLNIWFFIKTD5O4CBD3B5PFYULY/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":"2026-08-18T22:27:48Z","links":{"resolver":"https://pith.science/pith/NLNIWFFIKTD5O4CBD3B5PFYULY","bundle":"https://pith.science/pith/NLNIWFFIKTD5O4CBD3B5PFYULY/bundle.json","state":"https://pith.science/pith/NLNIWFFIKTD5O4CBD3B5PFYULY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLNIWFFIKTD5O4CBD3B5PFYULY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NLNIWFFIKTD5O4CBD3B5PFYULY","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":"d2ec179f36c3f9b806158f494450f9218855788e7fb293f71741eed571d41c9b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-24T12:28:03Z","title_canon_sha256":"d958ca423c1624a4717f07ddf4a742adc235163d2252ed62bb80bd3cf58cc680"},"schema_version":"1.0","source":{"id":"2407.17227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17227","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17227v1","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17227","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"NLNIWFFIKTD5","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"pith_short_16","alias_value":"NLNIWFFIKTD5O4CB","created_at":"2026-07-05T08:48:04Z"},{"alias_kind":"pith_short_8","alias_value":"NLNIWFFI","created_at":"2026-07-05T08:48:04Z"}],"graph_snapshots":[{"event_id":"sha256:231a6e7b894f4d1d7bab3524b371d47d81a39fcd342fdf44b6fb0a96146bca37","target":"graph","created_at":"2026-07-05T08:48:04Z","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/2407.17227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large language models have presented promising results in aiding formal mathematical reasoning. However, their performance is restricted due to the scarcity of formal theorem-proving data, which requires additional effort to be extracted from raw formal language corpora. Meanwhile, a significant amount of human-written formal language corpora remains underutilized. To address this issue, we propose LEAN-GitHub, a dataset consisting of large-scale formal data extracted from almost all Lean 4 repositories on GitHub. After fine-tuning InternLM-math-plus on this dataset, our model achiev","authors_text":"Dahua Lin, Jiayu Wang, Kai Chen, Zijian Wu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-24T12:28:03Z","title":"LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17227","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":"sha256:999968143bf9de462834b8d375bed65b80fc7dbfb8b344f4f5126273ac977e6f","target":"record","created_at":"2026-07-05T08:48:04Z","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":"d2ec179f36c3f9b806158f494450f9218855788e7fb293f71741eed571d41c9b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-24T12:28:03Z","title_canon_sha256":"d958ca423c1624a4717f07ddf4a742adc235163d2252ed62bb80bd3cf58cc680"},"schema_version":"1.0","source":{"id":"2407.17227","kind":"arxiv","version":1}},"canonical_sha256":"6ada8b14a854c7d770411ec3d797145e10aaddde2df5ba307f409435e848c430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ada8b14a854c7d770411ec3d797145e10aaddde2df5ba307f409435e848c430","first_computed_at":"2026-07-05T08:48:04.132455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:04.132455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LdlrB8bWufP4GiOzCexs80PJ+wp9Zz99W+pljJ6VuR+GXy8Gs8H7MxGB4cUUMlsCScIkIAVYEJmz4xkFPxfyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:04.132884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:999968143bf9de462834b8d375bed65b80fc7dbfb8b344f4f5126273ac977e6f","sha256:231a6e7b894f4d1d7bab3524b371d47d81a39fcd342fdf44b6fb0a96146bca37"],"state_sha256":"34da7c288223f46ccb9f81875cff678e31a1188ba56901aa4ae50440a9125073"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kHeQgaqUHL2aUc5O6ZLegcFWf2bX/9ok92onsjIT4KajUcMa+TfqJVPj7G92mMzaB1osWc/nLvHeM3G5+kv0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:27:48.243630Z","bundle_sha256":"9858eee5ce1672582d8eda62a89a1c60b598aae0de354c8318b0179b2e4ca028"}}