{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:E6BVFDCZ6KMNJXH365IGB2PZ4P","short_pith_number":"pith:E6BVFDCZ","schema_version":"1.0","canonical_sha256":"2783528c59f298d4dcfbf75060e9f9e3f0af2d8781a16b21565f6255d8f49aac","source":{"kind":"arxiv","id":"1912.03417","version":1},"attestation_state":"computed","paper":{"title":"AutoBlock: A Hands-off Blocking Framework for Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Bunyamin Sisman, Christos Faloutsos, David Page, Hao Wei, Wei Zhang, Xin Luna Dong","submitted_at":"2019-12-07T02:42:48Z","abstract_excerpt":"Entity matching seeks to identify data records over one or multiple data sources that refer to the same real-world entity. Virtually every entity matching task on large datasets requires blocking, a step that reduces the number of record pairs to be matched. However, most of the traditional blocking methods are learning-free and key-based, and their successes are largely built on laborious human effort in cleaning data and designing blocking keys.\n  In this paper, we propose AutoBlock, a novel hands-off blocking framework for entity matching, based on similarity-preserving representation learn"},"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":"1912.03417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-12-07T02:42:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a89c7f69e48bf4814a15a97bba1ab5e1303cfbe6bebf818e74d44c642b4bbc9a","abstract_canon_sha256":"8c318c8e8723692eaa6298422a0ff9309fdfb2a278f5bb2cf032b70b313b6fec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:45.308239Z","signature_b64":"j/dVtFstiGBSo5Dbz5pVEE4HwkP27iSKuSJQMnkkmWZeYiuJFJunW50Z7cl2gqLJOuN2BRbN/MSQD9VGyDMkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2783528c59f298d4dcfbf75060e9f9e3f0af2d8781a16b21565f6255d8f49aac","last_reissued_at":"2026-07-05T00:24:45.307828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:45.307828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoBlock: A Hands-off Blocking Framework for Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Bunyamin Sisman, Christos Faloutsos, David Page, Hao Wei, Wei Zhang, Xin Luna Dong","submitted_at":"2019-12-07T02:42:48Z","abstract_excerpt":"Entity matching seeks to identify data records over one or multiple data sources that refer to the same real-world entity. Virtually every entity matching task on large datasets requires blocking, a step that reduces the number of record pairs to be matched. However, most of the traditional blocking methods are learning-free and key-based, and their successes are largely built on laborious human effort in cleaning data and designing blocking keys.\n  In this paper, we propose AutoBlock, a novel hands-off blocking framework for entity matching, based on similarity-preserving representation learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03417","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.03417/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":"1912.03417","created_at":"2026-07-05T00:24:45.307892+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03417v1","created_at":"2026-07-05T00:24:45.307892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03417","created_at":"2026-07-05T00:24:45.307892+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6BVFDCZ6KMN","created_at":"2026-07-05T00:24:45.307892+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6BVFDCZ6KMNJXH3","created_at":"2026-07-05T00:24:45.307892+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6BVFDCZ","created_at":"2026-07-05T00:24:45.307892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04006","citing_title":"TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistency","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P","json":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P.json","graph_json":"https://pith.science/api/pith-number/E6BVFDCZ6KMNJXH365IGB2PZ4P/graph.json","events_json":"https://pith.science/api/pith-number/E6BVFDCZ6KMNJXH365IGB2PZ4P/events.json","paper":"https://pith.science/paper/E6BVFDCZ"},"agent_actions":{"view_html":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P","download_json":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P.json","view_paper":"https://pith.science/paper/E6BVFDCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03417&json=true","fetch_graph":"https://pith.science/api/pith-number/E6BVFDCZ6KMNJXH365IGB2PZ4P/graph.json","fetch_events":"https://pith.science/api/pith-number/E6BVFDCZ6KMNJXH365IGB2PZ4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P/action/storage_attestation","attest_author":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P/action/author_attestation","sign_citation":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P/action/citation_signature","submit_replication":"https://pith.science/pith/E6BVFDCZ6KMNJXH365IGB2PZ4P/action/replication_record"}},"created_at":"2026-07-05T00:24:45.307892+00:00","updated_at":"2026-07-05T00:24:45.307892+00:00"}