{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:32FYYQ7JFWFWFVWGZKVI63IM5G","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":"842626a891be58750561ec36858025c0bd9a0f3d6572caa70b9b6294692ae4ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2011-11-15T23:32:34Z","title_canon_sha256":"07eb2308f2f851f7dceb59b1469a22605d16e9248cd3d706a8c5671ee16daab3"},"schema_version":"1.0","source":{"id":"1111.3689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1111.3689","created_at":"2026-05-18T04:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"1111.3689v1","created_at":"2026-05-18T04:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1111.3689","created_at":"2026-05-18T04:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"32FYYQ7JFWFW","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"32FYYQ7JFWFWFVWG","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"32FYYQ7J","created_at":"2026-05-18T12:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:96c433b2b6328190fc927792405975ddaab610395dc772e7dea06bb95381bee6","target":"graph","created_at":"2026-05-18T04:08:13Z","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":"De-duplication---identification of distinct records referring to the same real-world entity---is a well-known challenge in data integration. Since very large datasets prohibit the comparison of every pair of records, {\\em blocking} has been identified as a technique of dividing the dataset for pairwise comparisons, thereby trading off {\\em recall} of identified duplicates for {\\em efficiency}. Traditional de-duplication tasks, while challenging, typically involved a fixed schema such as Census data or medical records. However, with the presence of large, diverse sets of structured data on the ","authors_text":"Anish Das Sarma, Ankur Jain, Ashwin Machanavajjhala, Philip Bohannon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2011-11-15T23:32:34Z","title":"CBLOCK: An Automatic Blocking Mechanism for Large-Scale De-duplication Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1111.3689","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:fa1ac182db896259cf815b4f2bda911aa0c131d9346d063bbdf0f0beda30182d","target":"record","created_at":"2026-05-18T04:08:13Z","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":"842626a891be58750561ec36858025c0bd9a0f3d6572caa70b9b6294692ae4ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2011-11-15T23:32:34Z","title_canon_sha256":"07eb2308f2f851f7dceb59b1469a22605d16e9248cd3d706a8c5671ee16daab3"},"schema_version":"1.0","source":{"id":"1111.3689","kind":"arxiv","version":1}},"canonical_sha256":"de8b8c43e92d8b62d6c6caaa8f6d0ce9b3cf5fce69b081b01c3d34d6eb12a260","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de8b8c43e92d8b62d6c6caaa8f6d0ce9b3cf5fce69b081b01c3d34d6eb12a260","first_computed_at":"2026-05-18T04:08:13.261658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:08:13.261658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O8++Yb2JHeRG/zQUh3DahHZGs+KiEBb2Crba45Jtg2p2pA4BpRJb2dc1l+tTtYNka9Bs7tUOJZEB+kJqVb4jAw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:08:13.262124Z","signed_message":"canonical_sha256_bytes"},"source_id":"1111.3689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa1ac182db896259cf815b4f2bda911aa0c131d9346d063bbdf0f0beda30182d","sha256:96c433b2b6328190fc927792405975ddaab610395dc772e7dea06bb95381bee6"],"state_sha256":"dc89a196cbc7d2c99ad1fd052d75d471939e7ec39badbbebf64357c3cc3e35b2"}