{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VAPFWVRBFNAOP6EHPQEHGP3UXD","short_pith_number":"pith:VAPFWVRB","schema_version":"1.0","canonical_sha256":"a81e5b56212b40e7f8877c08733f74b8cc195bf16a0e10ea2610a0ea80ef608f","source":{"kind":"arxiv","id":"2411.05409","version":3},"attestation_state":"computed","paper":{"title":"Web Archives Metadata Generation with GPT-4o: Challenges and Insights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DL","authors_text":"Abigail Yongping Huang, Ashwin Nair, Tianrui Liu, Zhen Rong Goh","submitted_at":"2024-11-08T08:59:40Z","abstract_excerpt":"Current metadata creation for web archives is time consuming and costly due to reliance on human effort. This paper explores the use of gpt-4o for metadata generation within the Web Archive Singapore, focusing on scalability, efficiency, and cost effectiveness. We processed 112 Web ARChive (WARC) files using data reduction techniques, achieving a notable 99.9% reduction in metadata generation costs. By prompt engineering, we generated titles and abstracts, which were evaluated both intrinsically using Levenshtein Distance and BERTScore, and extrinsically with human cataloguers using McNemar's "},"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":"2411.05409","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2024-11-08T08:59:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16ea185dde9edb91f936771779e2b78ec41ab4d3f004eefe36b6a1ddd1ac6f6a","abstract_canon_sha256":"869bf3f877f3706c58c0ca8a4720306af455b8bd460bd7250879f489ff11a69c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:08.551287Z","signature_b64":"rBHYX2H1NPyB+S/hRCMPBNbvBYFfwr9d/cb6eQiZOCrqQwZ/+izvpXRzx707bwo+95JkEwRBTE+8yN0H9WBHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a81e5b56212b40e7f8877c08733f74b8cc195bf16a0e10ea2610a0ea80ef608f","last_reissued_at":"2026-07-05T11:24:08.550679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:08.550679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Web Archives Metadata Generation with GPT-4o: Challenges and Insights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DL","authors_text":"Abigail Yongping Huang, Ashwin Nair, Tianrui Liu, Zhen Rong Goh","submitted_at":"2024-11-08T08:59:40Z","abstract_excerpt":"Current metadata creation for web archives is time consuming and costly due to reliance on human effort. This paper explores the use of gpt-4o for metadata generation within the Web Archive Singapore, focusing on scalability, efficiency, and cost effectiveness. We processed 112 Web ARChive (WARC) files using data reduction techniques, achieving a notable 99.9% reduction in metadata generation costs. By prompt engineering, we generated titles and abstracts, which were evaluated both intrinsically using Levenshtein Distance and BERTScore, and extrinsically with human cataloguers using McNemar's "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05409","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/2411.05409/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.05409","created_at":"2026-07-05T11:24:08.550739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05409v3","created_at":"2026-07-05T11:24:08.550739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05409","created_at":"2026-07-05T11:24:08.550739+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAPFWVRBFNAO","created_at":"2026-07-05T11:24:08.550739+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAPFWVRBFNAOP6EH","created_at":"2026-07-05T11:24:08.550739+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAPFWVRB","created_at":"2026-07-05T11:24:08.550739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD","json":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD.json","graph_json":"https://pith.science/api/pith-number/VAPFWVRBFNAOP6EHPQEHGP3UXD/graph.json","events_json":"https://pith.science/api/pith-number/VAPFWVRBFNAOP6EHPQEHGP3UXD/events.json","paper":"https://pith.science/paper/VAPFWVRB"},"agent_actions":{"view_html":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD","download_json":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD.json","view_paper":"https://pith.science/paper/VAPFWVRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05409&json=true","fetch_graph":"https://pith.science/api/pith-number/VAPFWVRBFNAOP6EHPQEHGP3UXD/graph.json","fetch_events":"https://pith.science/api/pith-number/VAPFWVRBFNAOP6EHPQEHGP3UXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/action/storage_attestation","attest_author":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/action/author_attestation","sign_citation":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/action/citation_signature","submit_replication":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/action/replication_record"}},"created_at":"2026-07-05T11:24:08.550739+00:00","updated_at":"2026-07-05T11:24:08.550739+00:00"}