{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UUEFKG7JJELDOG2LRWWJ65HANM","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":"be4c8d83c10d658a7be00c95ee40490af52cda59e01c4fecd677f0d5148cde83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-10T17:05:40Z","title_canon_sha256":"caa37d277cf9c8f8680bbd790091033bc3ef21e026e3f1b6a50e366228cc4f4b"},"schema_version":"1.0","source":{"id":"1704.02955","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.02955","created_at":"2026-05-17T23:41:01Z"},{"alias_kind":"arxiv_version","alias_value":"1704.02955v2","created_at":"2026-05-17T23:41:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02955","created_at":"2026-05-17T23:41:01Z"},{"alias_kind":"pith_short_12","alias_value":"UUEFKG7JJELD","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UUEFKG7JJELDOG2L","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UUEFKG7J","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:eb005c39073536c59f6f5d3fce2330baf118115c824d85a5fd3e34f61e92dd04","target":"graph","created_at":"2026-05-17T23:41:01Z","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":"We consider the problem of duplicate detection in noisy and incomplete data: given a large data set in which each record has multiple entries (attributes), detect which distinct records refer to the same real world entity. This task is complicated by noise (such as misspellings) and missing data, which can lead to records being different, despite referring to the same entity. Our method consists of three main steps: creating a similarity score between records, grouping records together into \"unique entities\", and refining the groups. We compare various methods for creating similarity scores be","authors_text":"Andrea L. Bertozzi, Anna Ma, Blake Hunter, Daniel Moyer, Ryan de Vera, Yves van Gennip","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-10T17:05:40Z","title":"Unsupervised record matching with noisy and incomplete data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02955","kind":"arxiv","version":2},"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:dc94d193679b91746d068302cb05b1724a71ae2e7eb2ff27441be0ac9543e4e4","target":"record","created_at":"2026-05-17T23:41:01Z","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":"be4c8d83c10d658a7be00c95ee40490af52cda59e01c4fecd677f0d5148cde83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-10T17:05:40Z","title_canon_sha256":"caa37d277cf9c8f8680bbd790091033bc3ef21e026e3f1b6a50e366228cc4f4b"},"schema_version":"1.0","source":{"id":"1704.02955","kind":"arxiv","version":2}},"canonical_sha256":"a508551be94916371b4b8dac9f74e06b167b1720d64e72a7bc65052a5e217969","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a508551be94916371b4b8dac9f74e06b167b1720d64e72a7bc65052a5e217969","first_computed_at":"2026-05-17T23:41:01.541448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:01.541448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FajKcsgW1IWENxQqn2lGrPzbg5nGvIRxp+nZhm9YXuhnP+FCtNUq6EeWXwNxgsJE3avUv8gWXDB1GUCKq+TaAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:01.542113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.02955","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc94d193679b91746d068302cb05b1724a71ae2e7eb2ff27441be0ac9543e4e4","sha256:eb005c39073536c59f6f5d3fce2330baf118115c824d85a5fd3e34f61e92dd04"],"state_sha256":"358b015768d355d004a2a4d09f52d902e638f8508f39903de0c2dc8c4c91c927"}