{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZLOG56AIBQEDG2P72M5RECF3TL","short_pith_number":"pith:ZLOG56AI","schema_version":"1.0","canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","source":{"kind":"arxiv","id":"1810.05497","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Blocking with An Application to the Syrian Conflict","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ML"],"primary_cat":"cs.DB","authors_text":"Anshumali Shrivastava, Rebecca C. Steorts","submitted_at":"2018-10-11T01:16:31Z","abstract_excerpt":"Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce $k$-means locality sensitive hashing (KLSH), which is based upon the information retrieval literature and clusters similar records into blocks using a vector-space representation and projections. Second, we introduce a subquadratic variant of LSH to the literature, known as Densified One Permutation Hashing (DOPH). Third, we propose "},"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":"1810.05497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-11T01:16:31Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"title_canon_sha256":"ce56ee20274b4a2e5ef9177e21968db1fc201abbdebb47d6aac35760ae9fa563","abstract_canon_sha256":"2426daa1c6b1f8319f96b45e1184306166c1651a078ee713ab55d244cc60d6eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:30.319611Z","signature_b64":"QOwGie992bYR1ItpdE095bFVt4CpToYs2JnoaWn3Lim4ffN+T0XH6SssdIW3KD/XHZyMIrAXETvr1qoMrJyFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","last_reissued_at":"2026-05-18T00:03:30.318999Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:30.318999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Blocking with An Application to the Syrian Conflict","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ML"],"primary_cat":"cs.DB","authors_text":"Anshumali Shrivastava, Rebecca C. Steorts","submitted_at":"2018-10-11T01:16:31Z","abstract_excerpt":"Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce $k$-means locality sensitive hashing (KLSH), which is based upon the information retrieval literature and clusters similar records into blocks using a vector-space representation and projections. Second, we introduce a subquadratic variant of LSH to the literature, known as Densified One Permutation Hashing (DOPH). Third, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05497","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":"1810.05497","created_at":"2026-05-18T00:03:30.319093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05497v1","created_at":"2026-05-18T00:03:30.319093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05497","created_at":"2026-05-18T00:03:30.319093+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLOG56AIBQED","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLOG56AIBQEDG2P7","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLOG56AI","created_at":"2026-05-18T12:33:07.085635+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/ZLOG56AIBQEDG2P72M5RECF3TL","json":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL.json","graph_json":"https://pith.science/api/pith-number/ZLOG56AIBQEDG2P72M5RECF3TL/graph.json","events_json":"https://pith.science/api/pith-number/ZLOG56AIBQEDG2P72M5RECF3TL/events.json","paper":"https://pith.science/paper/ZLOG56AI"},"agent_actions":{"view_html":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL","download_json":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL.json","view_paper":"https://pith.science/paper/ZLOG56AI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05497&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLOG56AIBQEDG2P72M5RECF3TL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLOG56AIBQEDG2P72M5RECF3TL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/action/storage_attestation","attest_author":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/action/author_attestation","sign_citation":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/action/citation_signature","submit_replication":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/action/replication_record"}},"created_at":"2026-05-18T00:03:30.319093+00:00","updated_at":"2026-05-18T00:03:30.319093+00:00"}