{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OBIVX6GTBTCZOGLLKDZFWUO2UT","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":"a6db836b0be13d0e70175a860908a6a1ea2b466fcde5537465fb56f3aa66cd42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-08T18:25:48Z","title_canon_sha256":"b38fb461e694ad92a7b88415d13062940b87edae21f4baea0185c3ad093ffb75"},"schema_version":"1.0","source":{"id":"1804.02734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02734","created_at":"2026-05-18T00:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02734v1","created_at":"2026-05-18T00:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02734","created_at":"2026-05-18T00:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"OBIVX6GTBTCZ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OBIVX6GTBTCZOGLL","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OBIVX6GT","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:48bebc06751d672001f9497b4a766ed1e5f53a8f143ec81638cf11e69b997304","target":"graph","created_at":"2026-05-18T00:18:58Z","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"},"paper":{"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","authors_text":"Jamie Callan, Keyang Xu, Kyle Yingkai Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-08T18:25:48Z","title":"A Structure-Oriented Unsupervised Crawling Strategy for Social Media Sites"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02734","kind":"arxiv","version":1},"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":"sha256:6758bf350986057562589dadaa3fb89f4ef49ae1af4f27b517ddd794a2cc074e","target":"record","created_at":"2026-05-18T00:18:58Z","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":"a6db836b0be13d0e70175a860908a6a1ea2b466fcde5537465fb56f3aa66cd42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-08T18:25:48Z","title_canon_sha256":"b38fb461e694ad92a7b88415d13062940b87edae21f4baea0185c3ad093ffb75"},"schema_version":"1.0","source":{"id":"1804.02734","kind":"arxiv","version":1}},"canonical_sha256":"70515bf8d30cc597196b50f25b51daa4f8fcdfba0cc978a0e2f3f146e1a097d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70515bf8d30cc597196b50f25b51daa4f8fcdfba0cc978a0e2f3f146e1a097d8","first_computed_at":"2026-05-18T00:18:58.568909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:58.568909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oqa27nOwaOWJQHLTOxVOORTiV7FmpyhPeIPSVOq4P35fcswTUXqe3hZ79rZeNEA31xzXmYJ3ZMWw/lSPzl7dDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:58.569658Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6758bf350986057562589dadaa3fb89f4ef49ae1af4f27b517ddd794a2cc074e","sha256:48bebc06751d672001f9497b4a766ed1e5f53a8f143ec81638cf11e69b997304"],"state_sha256":"d38f26b85ae5cfef0f2e58708199a9f1711883e77b3523d84ac2abf7cac8fd57"}