{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7M4H5Y5DUZX2HLFEX2UTT3AK4S","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":"ec63394d2a855eecb3e36820141b9467653ed2e8cea91a28bc6b5ded3d912c30","cross_cats_sorted":["cs.LG","cs.SI","physics.soc-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-30T19:43:53Z","title_canon_sha256":"1ab2c690081ccb874b79af57b857bc9e7302b191e9ca9a91f73a4cf1120c5c96"},"schema_version":"1.0","source":{"id":"1905.00075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00075","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00075v1","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00075","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"7M4H5Y5DUZX2","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7M4H5Y5DUZX2HLFE","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7M4H5Y5D","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:f52c64dcae24c7ef4e2819ba773127b90e9ccbca2e608e9a87c1f8ea3a1d1b0f","target":"graph","created_at":"2026-05-17T23:47:15Z","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"},"paper":{"abstract_excerpt":"The arXiv has collected 1.5 million pre-print articles over 28 years, hosting literature from scientific fields including Physics, Mathematics, and Computer Science. Each pre-print features text, figures, authors, citations, categories, and other metadata. These rich, multi-modal features, combined with the natural graph structure---created by citation, affiliation, and co-authorship---makes the arXiv an exciting candidate for benchmarking next-generation models. Here we take the first necessary steps toward this goal, by providing a pipeline which standardizes and simplifies access to the arX","authors_text":"Alexander A. Alemi, Colin B. Clement, Kevin P. O'Keeffe, Matthew Bierbaum","cross_cats":["cs.LG","cs.SI","physics.soc-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-30T19:43:53Z","title":"On the Use of ArXiv as a Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00075","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":"sha256:0e7667088203a3fb34734f26c64314370eb2bbb4820c73cd724257872603b15e","target":"record","created_at":"2026-05-17T23:47:15Z","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":"ec63394d2a855eecb3e36820141b9467653ed2e8cea91a28bc6b5ded3d912c30","cross_cats_sorted":["cs.LG","cs.SI","physics.soc-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-30T19:43:53Z","title_canon_sha256":"1ab2c690081ccb874b79af57b857bc9e7302b191e9ca9a91f73a4cf1120c5c96"},"schema_version":"1.0","source":{"id":"1905.00075","kind":"arxiv","version":1}},"canonical_sha256":"fb387ee3a3a66fa3aca4bea939ec0ae4b92f9f86b5806e0b319a3c22853b163f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb387ee3a3a66fa3aca4bea939ec0ae4b92f9f86b5806e0b319a3c22853b163f","first_computed_at":"2026-05-17T23:47:15.264389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:15.264389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QtlmQhkK1P972yqXr9bCqvqlHLMikxQossA6lkn5RGwvpxXvwY6UNRoXVgDpne205nuvUXfuNXaXUZMZoXCMDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:15.264813Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e7667088203a3fb34734f26c64314370eb2bbb4820c73cd724257872603b15e","sha256:f52c64dcae24c7ef4e2819ba773127b90e9ccbca2e608e9a87c1f8ea3a1d1b0f"],"state_sha256":"56fdbd952771242023992c78394a28dd8b7483c6376525d4904c4f2adf80f9ae"}