{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7Y5SK4QBBLHUXEGPJMSGMRMXAH","short_pith_number":"pith:7Y5SK4QB","schema_version":"1.0","canonical_sha256":"fe3b2572010acf4b90cf4b2466459701e53d76499b483470b44fa50f99cfde9f","source":{"kind":"arxiv","id":"2303.03132","version":2},"attestation_state":"computed","paper":{"title":"SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Alexander Brinkmann, Christian Bizer, Roee Shraga","submitted_at":"2023-03-06T13:49:41Z","abstract_excerpt":"The goal of entity resolution is to identify records in multiple datasets that represent the same real-world entity. However, comparing all records across datasets can be computationally intensive, leading to long runtimes. To reduce these runtimes, entity resolution pipelines are constructed of two parts: a blocker that applies a computationally cheap method to select candidate record pairs, and a matcher that afterwards identifies matching pairs from this set using more expensive methods. This paper presents SC-Block, a blocking method that utilizes supervised contrastive learning for positi"},"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":"2303.03132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-03-06T13:49:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53afb0b0eefaf6053e53da78a311053c4d507f7e76258af3e43e81e9e4005fac","abstract_canon_sha256":"30b6bbff01d595ea0836ec1c7022ba1cc88c2f5bb2e247260b656cca2cdb5536"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:59.372599Z","signature_b64":"m8D2/6Gq7rrobBrx99DUQ2JP4Fr3eY8mhwcxjq29sjFd26xCyobk8gk7kELiWq8eudl1aEDyw8yHLs7gCIDwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe3b2572010acf4b90cf4b2466459701e53d76499b483470b44fa50f99cfde9f","last_reissued_at":"2026-07-05T06:23:59.372134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:59.372134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Alexander Brinkmann, Christian Bizer, Roee Shraga","submitted_at":"2023-03-06T13:49:41Z","abstract_excerpt":"The goal of entity resolution is to identify records in multiple datasets that represent the same real-world entity. However, comparing all records across datasets can be computationally intensive, leading to long runtimes. To reduce these runtimes, entity resolution pipelines are constructed of two parts: a blocker that applies a computationally cheap method to select candidate record pairs, and a matcher that afterwards identifies matching pairs from this set using more expensive methods. This paper presents SC-Block, a blocking method that utilizes supervised contrastive learning for positi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03132","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.03132/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2303.03132","created_at":"2026-07-05T06:23:59.372189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03132v2","created_at":"2026-07-05T06:23:59.372189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03132","created_at":"2026-07-05T06:23:59.372189+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Y5SK4QBBLHU","created_at":"2026-07-05T06:23:59.372189+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Y5SK4QBBLHUXEGP","created_at":"2026-07-05T06:23:59.372189+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Y5SK4QB","created_at":"2026-07-05T06:23:59.372189+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/7Y5SK4QBBLHUXEGPJMSGMRMXAH","json":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH.json","graph_json":"https://pith.science/api/pith-number/7Y5SK4QBBLHUXEGPJMSGMRMXAH/graph.json","events_json":"https://pith.science/api/pith-number/7Y5SK4QBBLHUXEGPJMSGMRMXAH/events.json","paper":"https://pith.science/paper/7Y5SK4QB"},"agent_actions":{"view_html":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH","download_json":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH.json","view_paper":"https://pith.science/paper/7Y5SK4QB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03132&json=true","fetch_graph":"https://pith.science/api/pith-number/7Y5SK4QBBLHUXEGPJMSGMRMXAH/graph.json","fetch_events":"https://pith.science/api/pith-number/7Y5SK4QBBLHUXEGPJMSGMRMXAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH/action/storage_attestation","attest_author":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH/action/author_attestation","sign_citation":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH/action/citation_signature","submit_replication":"https://pith.science/pith/7Y5SK4QBBLHUXEGPJMSGMRMXAH/action/replication_record"}},"created_at":"2026-07-05T06:23:59.372189+00:00","updated_at":"2026-07-05T06:23:59.372189+00:00"}