{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QS4CVMGLUBLQVB7LAW6PHGVN3I","short_pith_number":"pith:QS4CVMGL","schema_version":"1.0","canonical_sha256":"84b82ab0cba0570a87eb05bcf39aadda0f6a876437520ef27c5166fc0d7a816c","source":{"kind":"arxiv","id":"1905.12220","version":1},"attestation_state":"computed","paper":{"title":"Using Micro-collections in Social Media to Generate Seeds for Web Archive Collections","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DL","authors_text":"Alexander C. Nwala, Michael L. Nelson, Michele C. Weigle","submitted_at":"2019-05-29T05:19:58Z","abstract_excerpt":"In a Web plagued by disappearing resources, Web archive collections provide a valuable means of preserving Web resources important to the study of past events ranging from elections to disease outbreaks. These archived collections start with seed URIs (Uniform Resource Identifiers) hand-selected by curators. Curators produce high quality seeds by removing non-relevant URIs and adding URIs from credible and authoritative sources, but it is time consuming to collect these seeds. Two main strategies adopted by curators for discovering seeds include scraping Web (e.g., Google) Search Engine Result"},"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":"1905.12220","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2019-05-29T05:19:58Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"120a356624238a240f9e306e642dbf1bc61c9561e9814acd6d39a268c29c8a34","abstract_canon_sha256":"0505d2640a9e8c61fb40991cf8ad326db3f2d2f63d7841ceab7dfec18dfbf5ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:46.765845Z","signature_b64":"YjKHw6OhOV0Hoe0FpeNEZMfqBHVdcNZFiZIH1pF68B7/h9g53mR+MD7UKa0z1inHeEs3KOtf1HF9w8qhB8ZdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84b82ab0cba0570a87eb05bcf39aadda0f6a876437520ef27c5166fc0d7a816c","last_reissued_at":"2026-05-17T23:44:46.765216Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:46.765216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Micro-collections in Social Media to Generate Seeds for Web Archive Collections","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DL","authors_text":"Alexander C. Nwala, Michael L. Nelson, Michele C. Weigle","submitted_at":"2019-05-29T05:19:58Z","abstract_excerpt":"In a Web plagued by disappearing resources, Web archive collections provide a valuable means of preserving Web resources important to the study of past events ranging from elections to disease outbreaks. These archived collections start with seed URIs (Uniform Resource Identifiers) hand-selected by curators. Curators produce high quality seeds by removing non-relevant URIs and adding URIs from credible and authoritative sources, but it is time consuming to collect these seeds. Two main strategies adopted by curators for discovering seeds include scraping Web (e.g., Google) Search Engine Result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12220","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":"1905.12220","created_at":"2026-05-17T23:44:46.765341+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12220v1","created_at":"2026-05-17T23:44:46.765341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12220","created_at":"2026-05-17T23:44:46.765341+00:00"},{"alias_kind":"pith_short_12","alias_value":"QS4CVMGLUBLQ","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QS4CVMGLUBLQVB7L","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QS4CVMGL","created_at":"2026-05-18T12:33:27.125529+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/QS4CVMGLUBLQVB7LAW6PHGVN3I","json":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I.json","graph_json":"https://pith.science/api/pith-number/QS4CVMGLUBLQVB7LAW6PHGVN3I/graph.json","events_json":"https://pith.science/api/pith-number/QS4CVMGLUBLQVB7LAW6PHGVN3I/events.json","paper":"https://pith.science/paper/QS4CVMGL"},"agent_actions":{"view_html":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I","download_json":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I.json","view_paper":"https://pith.science/paper/QS4CVMGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12220&json=true","fetch_graph":"https://pith.science/api/pith-number/QS4CVMGLUBLQVB7LAW6PHGVN3I/graph.json","fetch_events":"https://pith.science/api/pith-number/QS4CVMGLUBLQVB7LAW6PHGVN3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I/action/storage_attestation","attest_author":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I/action/author_attestation","sign_citation":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I/action/citation_signature","submit_replication":"https://pith.science/pith/QS4CVMGLUBLQVB7LAW6PHGVN3I/action/replication_record"}},"created_at":"2026-05-17T23:44:46.765341+00:00","updated_at":"2026-05-17T23:44:46.765341+00:00"}