{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OBIVX6GTBTCZOGLLKDZFWUO2UT","short_pith_number":"pith:OBIVX6GT","schema_version":"1.0","canonical_sha256":"70515bf8d30cc597196b50f25b51daa4f8fcdfba0cc978a0e2f3f146e1a097d8","source":{"kind":"arxiv","id":"1804.02734","version":1},"attestation_state":"computed","paper":{"title":"A Structure-Oriented Unsupervised Crawling Strategy for Social Media Sites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jamie Callan, Keyang Xu, Kyle Yingkai Gao","submitted_at":"2018-04-08T18:25:48Z","abstract_excerpt":"Existing techniques for efficiently crawling social media sites rely on URL patterns, query logs, and human supervision. This paper describes SOUrCe, a structure-oriented unsupervised crawler that uses page structures to learn how to crawl a social media site efficiently. SOUrCe consists of two stages. During its unsupervised learning phase, SOUrCe constructs a sitemap that clusters pages based on their structural similarity and generates a navigation table that describes how the different types of pages in the site are linked together. During its harvesting phase, it uses the navigation table"},"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":"1804.02734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-08T18:25:48Z","cross_cats_sorted":[],"title_canon_sha256":"b38fb461e694ad92a7b88415d13062940b87edae21f4baea0185c3ad093ffb75","abstract_canon_sha256":"a6db836b0be13d0e70175a860908a6a1ea2b466fcde5537465fb56f3aa66cd42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:58.569658Z","signature_b64":"Oqa27nOwaOWJQHLTOxVOORTiV7FmpyhPeIPSVOq4P35fcswTUXqe3hZ79rZeNEA31xzXmYJ3ZMWw/lSPzl7dDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70515bf8d30cc597196b50f25b51daa4f8fcdfba0cc978a0e2f3f146e1a097d8","last_reissued_at":"2026-05-18T00:18:58.568909Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:58.568909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Structure-Oriented Unsupervised Crawling Strategy for Social Media Sites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jamie Callan, Keyang Xu, Kyle Yingkai Gao","submitted_at":"2018-04-08T18:25:48Z","abstract_excerpt":"Existing techniques for efficiently crawling social media sites rely on URL patterns, query logs, and human supervision. This paper describes SOUrCe, a structure-oriented unsupervised crawler that uses page structures to learn how to crawl a social media site efficiently. SOUrCe consists of two stages. During its unsupervised learning phase, SOUrCe constructs a sitemap that clusters pages based on their structural similarity and generates a navigation table that describes how the different types of pages in the site are linked together. During its harvesting phase, it uses the navigation table"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02734","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":"1804.02734","created_at":"2026-05-18T00:18:58.569030+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02734v1","created_at":"2026-05-18T00:18:58.569030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02734","created_at":"2026-05-18T00:18:58.569030+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBIVX6GTBTCZ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBIVX6GTBTCZOGLL","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBIVX6GT","created_at":"2026-05-18T12:32:43.782077+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/OBIVX6GTBTCZOGLLKDZFWUO2UT","json":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT.json","graph_json":"https://pith.science/api/pith-number/OBIVX6GTBTCZOGLLKDZFWUO2UT/graph.json","events_json":"https://pith.science/api/pith-number/OBIVX6GTBTCZOGLLKDZFWUO2UT/events.json","paper":"https://pith.science/paper/OBIVX6GT"},"agent_actions":{"view_html":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT","download_json":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT.json","view_paper":"https://pith.science/paper/OBIVX6GT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02734&json=true","fetch_graph":"https://pith.science/api/pith-number/OBIVX6GTBTCZOGLLKDZFWUO2UT/graph.json","fetch_events":"https://pith.science/api/pith-number/OBIVX6GTBTCZOGLLKDZFWUO2UT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT/action/storage_attestation","attest_author":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT/action/author_attestation","sign_citation":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT/action/citation_signature","submit_replication":"https://pith.science/pith/OBIVX6GTBTCZOGLLKDZFWUO2UT/action/replication_record"}},"created_at":"2026-05-18T00:18:58.569030+00:00","updated_at":"2026-05-18T00:18:58.569030+00:00"}