{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7M4H5Y5DUZX2HLFEX2UTT3AK4S","short_pith_number":"pith:7M4H5Y5D","schema_version":"1.0","canonical_sha256":"fb387ee3a3a66fa3aca4bea939ec0ae4b92f9f86b5806e0b319a3c22853b163f","source":{"kind":"arxiv","id":"1905.00075","version":1},"attestation_state":"computed","paper":{"title":"On the Use of ArXiv as a Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI","physics.soc-ph"],"primary_cat":"cs.IR","authors_text":"Alexander A. Alemi, Colin B. Clement, Kevin P. O'Keeffe, Matthew Bierbaum","submitted_at":"2019-04-30T19:43:53Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.00075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-30T19:43:53Z","cross_cats_sorted":["cs.LG","cs.SI","physics.soc-ph"],"title_canon_sha256":"1ab2c690081ccb874b79af57b857bc9e7302b191e9ca9a91f73a4cf1120c5c96","abstract_canon_sha256":"ec63394d2a855eecb3e36820141b9467653ed2e8cea91a28bc6b5ded3d912c30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:15.264813Z","signature_b64":"QtlmQhkK1P972yqXr9bCqvqlHLMikxQossA6lkn5RGwvpxXvwY6UNRoXVgDpne205nuvUXfuNXaXUZMZoXCMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb387ee3a3a66fa3aca4bea939ec0ae4b92f9f86b5806e0b319a3c22853b163f","last_reissued_at":"2026-05-17T23:47:15.264389Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:15.264389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Use of ArXiv as a Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI","physics.soc-ph"],"primary_cat":"cs.IR","authors_text":"Alexander A. Alemi, Colin B. Clement, Kevin P. O'Keeffe, Matthew Bierbaum","submitted_at":"2019-04-30T19:43:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00075","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.00075","created_at":"2026-05-17T23:47:15.264455+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00075v1","created_at":"2026-05-17T23:47:15.264455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00075","created_at":"2026-05-17T23:47:15.264455+00:00"},{"alias_kind":"pith_short_12","alias_value":"7M4H5Y5DUZX2","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7M4H5Y5DUZX2HLFE","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7M4H5Y5D","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.23694","citing_title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2603.04759","citing_title":"Stacked from One: Multi-Scale Self-Injection for Context Window Extension","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08568","citing_title":"Can We Still Hear the Accent? Investigating the Resilience of Native Language Signals in the LLM Era","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12227","citing_title":"Combining On-Policy Optimization and Distillation for Long-Context Reasoning in Large Language Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21304","citing_title":"PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20927","citing_title":"Hidden Secrets in the arXiv: Discovering, Analyzing, and Preventing Unintentional Information Disclosure in Source Files of Scientific Preprints","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S","json":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S.json","graph_json":"https://pith.science/api/pith-number/7M4H5Y5DUZX2HLFEX2UTT3AK4S/graph.json","events_json":"https://pith.science/api/pith-number/7M4H5Y5DUZX2HLFEX2UTT3AK4S/events.json","paper":"https://pith.science/paper/7M4H5Y5D"},"agent_actions":{"view_html":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S","download_json":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S.json","view_paper":"https://pith.science/paper/7M4H5Y5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00075&json=true","fetch_graph":"https://pith.science/api/pith-number/7M4H5Y5DUZX2HLFEX2UTT3AK4S/graph.json","fetch_events":"https://pith.science/api/pith-number/7M4H5Y5DUZX2HLFEX2UTT3AK4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S/action/storage_attestation","attest_author":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S/action/author_attestation","sign_citation":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S/action/citation_signature","submit_replication":"https://pith.science/pith/7M4H5Y5DUZX2HLFEX2UTT3AK4S/action/replication_record"}},"created_at":"2026-05-17T23:47:15.264455+00:00","updated_at":"2026-05-17T23:47:15.264455+00:00"}