{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VAPFWVRBFNAOP6EHPQEHGP3UXD","short_pith_number":"pith:VAPFWVRB","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"},"canonical_sha256":"a81e5b56212b40e7f8877c08733f74b8cc195bf16a0e10ea2610a0ea80ef608f","source":{"kind":"arxiv","id":"2411.05409","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05409","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05409v3","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05409","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"VAPFWVRBFNAO","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"VAPFWVRBFNAOP6EH","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"VAPFWVRB","created_at":"2026-07-05T11:24:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VAPFWVRBFNAOP6EHPQEHGP3UXD","target":"record","payload":{"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"},"canonical_sha256":"a81e5b56212b40e7f8877c08733f74b8cc195bf16a0e10ea2610a0ea80ef608f","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"},"source_kind":"arxiv","source_id":"2411.05409","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":"2026-07-05T11:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sf+MUQaykZVGtOm28DCpB+XX7hULTLtV0bgcUf5qs8E8nxP7Cxn5g+tgk84CJAseEOajUsEc2+VvgpzA3QU6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:12:29.263588Z"},"content_sha256":"d2bb3112833b6994781f4961c248f2b79b8dd0736f2df47a368f52a488fcb604","schema_version":"1.0","event_id":"sha256:d2bb3112833b6994781f4961c248f2b79b8dd0736f2df47a368f52a488fcb604"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VAPFWVRBFNAOP6EHPQEHGP3UXD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wmKDI5HUCP3b5TiYfUUFZ+8y32EqCazmApY2pC0kFrBFyLBYWwJx3qd/Vt+2Gr/qDir3WMr0d/p8jHtqnAK+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:12:29.263991Z"},"content_sha256":"276357bbabba140cd233cba1475f925193fa6dac0fbba265a5cd733f67819576","schema_version":"1.0","event_id":"sha256:276357bbabba140cd233cba1475f925193fa6dac0fbba265a5cd733f67819576"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/bundle.json","state_url":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/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":"2026-07-06T23:12:29Z","links":{"resolver":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD","bundle":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/bundle.json","state":"https://pith.science/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VAPFWVRBFNAOP6EHPQEHGP3UXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VAPFWVRBFNAOP6EHPQEHGP3UXD","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":"869bf3f877f3706c58c0ca8a4720306af455b8bd460bd7250879f489ff11a69c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2024-11-08T08:59:40Z","title_canon_sha256":"16ea185dde9edb91f936771779e2b78ec41ab4d3f004eefe36b6a1ddd1ac6f6a"},"schema_version":"1.0","source":{"id":"2411.05409","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05409","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05409v3","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05409","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"VAPFWVRBFNAO","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"VAPFWVRBFNAOP6EH","created_at":"2026-07-05T11:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"VAPFWVRB","created_at":"2026-07-05T11:24:08Z"}],"graph_snapshots":[{"event_id":"sha256:276357bbabba140cd233cba1475f925193fa6dac0fbba265a5cd733f67819576","target":"graph","created_at":"2026-07-05T11:24:08Z","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/2411.05409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Abigail Yongping Huang, Ashwin Nair, Tianrui Liu, Zhen Rong Goh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2024-11-08T08:59:40Z","title":"Web Archives Metadata Generation with GPT-4o: Challenges and Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05409","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:d2bb3112833b6994781f4961c248f2b79b8dd0736f2df47a368f52a488fcb604","target":"record","created_at":"2026-07-05T11:24:08Z","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":"869bf3f877f3706c58c0ca8a4720306af455b8bd460bd7250879f489ff11a69c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2024-11-08T08:59:40Z","title_canon_sha256":"16ea185dde9edb91f936771779e2b78ec41ab4d3f004eefe36b6a1ddd1ac6f6a"},"schema_version":"1.0","source":{"id":"2411.05409","kind":"arxiv","version":3}},"canonical_sha256":"a81e5b56212b40e7f8877c08733f74b8cc195bf16a0e10ea2610a0ea80ef608f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a81e5b56212b40e7f8877c08733f74b8cc195bf16a0e10ea2610a0ea80ef608f","first_computed_at":"2026-07-05T11:24:08.550679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:08.550679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rBHYX2H1NPyB+S/hRCMPBNbvBYFfwr9d/cb6eQiZOCrqQwZ/+izvpXRzx707bwo+95JkEwRBTE+8yN0H9WBHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:08.551287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05409","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2bb3112833b6994781f4961c248f2b79b8dd0736f2df47a368f52a488fcb604","sha256:276357bbabba140cd233cba1475f925193fa6dac0fbba265a5cd733f67819576"],"state_sha256":"57842d6d2fa199739c404a5b2706e415fb9a726f01b83fb704dd59878f2e4d62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odLJBIX4sUo4N8qsjycpLqAYjEWe9UPF+ZHrDWSeWDXCgvUU5uyu+dphTAQ0KAjv31Zqox/hpn0UHVSyMaj1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:12:29.266099Z","bundle_sha256":"e287042d1ca3bf2613810b2b3b356f0d40bfcf48fbf7584179e4bfcb2e3bc896"}}