{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:KFFRYICXPZGJHHG65O6SJTMIHD","short_pith_number":"pith:KFFRYICX","schema_version":"1.0","canonical_sha256":"514b1c20577e4c939cdeebbd24cd8838f3984bdd66d01616bc93f8f1e79c50fd","source":{"kind":"arxiv","id":"1508.03116","version":1},"attestation_state":"computed","paper":{"title":"Query-Driven Sampling for Collective Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christan Grant, Daisy Zhe Wang, Michael L. Wick","submitted_at":"2015-08-13T04:23:58Z","abstract_excerpt":"Probabilistic databases play a preeminent role in the processing and management of uncertain data. Recently, many database research efforts have integrated probabilistic models into databases to support tasks such as information extraction and labeling. Many of these efforts are based on batch oriented inference which inhibits a realtime workflow. One important task is entity resolution (ER). ER is the process of determining records (mentions) in a database that correspond to the same real-world entity. Traditional pairwise ER methods can lead to inconsistencies and low accuracy due to localiz"},"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":"1508.03116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-08-13T04:23:58Z","cross_cats_sorted":[],"title_canon_sha256":"4a7f72ddeaeb193fd22a852fd074f6cf38a5cd9ff64bd412fa7c4e5c5789a1e4","abstract_canon_sha256":"c605ac8f2fde59383cc3fcca3d5901e91510b4ed42f27fa579f26ebc744a2009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:21.671743Z","signature_b64":"JonGX23vdz1halwx6vKA6YLFdXGicREddel+oy9a+V79bkvLLKwXxw0CZW3452sE09Y+ob55rDDJPDdcK9YVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514b1c20577e4c939cdeebbd24cd8838f3984bdd66d01616bc93f8f1e79c50fd","last_reissued_at":"2026-05-18T01:35:21.670979Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:21.670979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-Driven Sampling for Collective Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christan Grant, Daisy Zhe Wang, Michael L. Wick","submitted_at":"2015-08-13T04:23:58Z","abstract_excerpt":"Probabilistic databases play a preeminent role in the processing and management of uncertain data. Recently, many database research efforts have integrated probabilistic models into databases to support tasks such as information extraction and labeling. Many of these efforts are based on batch oriented inference which inhibits a realtime workflow. One important task is entity resolution (ER). ER is the process of determining records (mentions) in a database that correspond to the same real-world entity. Traditional pairwise ER methods can lead to inconsistencies and low accuracy due to localiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03116","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":"1508.03116","created_at":"2026-05-18T01:35:21.671109+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.03116v1","created_at":"2026-05-18T01:35:21.671109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03116","created_at":"2026-05-18T01:35:21.671109+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFFRYICXPZGJ","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFFRYICXPZGJHHG6","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFFRYICX","created_at":"2026-05-18T12:29:27.538025+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/KFFRYICXPZGJHHG65O6SJTMIHD","json":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD.json","graph_json":"https://pith.science/api/pith-number/KFFRYICXPZGJHHG65O6SJTMIHD/graph.json","events_json":"https://pith.science/api/pith-number/KFFRYICXPZGJHHG65O6SJTMIHD/events.json","paper":"https://pith.science/paper/KFFRYICX"},"agent_actions":{"view_html":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD","download_json":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD.json","view_paper":"https://pith.science/paper/KFFRYICX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.03116&json=true","fetch_graph":"https://pith.science/api/pith-number/KFFRYICXPZGJHHG65O6SJTMIHD/graph.json","fetch_events":"https://pith.science/api/pith-number/KFFRYICXPZGJHHG65O6SJTMIHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD/action/storage_attestation","attest_author":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD/action/author_attestation","sign_citation":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD/action/citation_signature","submit_replication":"https://pith.science/pith/KFFRYICXPZGJHHG65O6SJTMIHD/action/replication_record"}},"created_at":"2026-05-18T01:35:21.671109+00:00","updated_at":"2026-05-18T01:35:21.671109+00:00"}