{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HCAL4YSBTZBBMGGBEWYGKMQIQN","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":"5465fb9900be29d6d895e906abb9ce725f7e98df54721a196184741e8b2a88bd","cross_cats_sorted":["stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-08-19T16:26:21Z","title_canon_sha256":"309b79a59a2fec97ab32755abcb49391b4a038c189e345946c8677f37d8a1a0d"},"schema_version":"1.0","source":{"id":"2108.08773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08773","created_at":"2026-07-05T03:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08773v1","created_at":"2026-07-05T03:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08773","created_at":"2026-07-05T03:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"HCAL4YSBTZBB","created_at":"2026-07-05T03:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"HCAL4YSBTZBBMGGB","created_at":"2026-07-05T03:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"HCAL4YSB","created_at":"2026-07-05T03:07:13Z"}],"graph_snapshots":[{"event_id":"sha256:9048dd6e3484cef5f47c30d5e8e464a1c8ee990897c00b369fac987806dab101","target":"graph","created_at":"2026-07-05T03:07:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.08773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pedigree data contain family history information that is used to analyze hereditary diseases. These clinical data sets may contain duplicate records due to the same family visiting a clinic multiple times or a clinician entering multiple versions of the family for testing purposes. Inferences drawn from the data or using them for training or validation without removing the duplicates could lead to invalid conclusions, and hence identifying the duplicates is essential. Since family structures can be complex, existing deduplication algorithms cannot be applied directly. We first motivate the imp","authors_text":"Danielle Braun, Matthew Ploenzke, Theodore Huang","cross_cats":["stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-08-19T16:26:21Z","title":"SNIP: An Adaptation of Sorted Neighborhood Methods for Deduplicating Pedigree Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08773","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":"sha256:0d079613148542b4166a8d58f4175a53d2b67239c09d04807a2f5b59f09ebdb0","target":"record","created_at":"2026-07-05T03:07:13Z","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":"5465fb9900be29d6d895e906abb9ce725f7e98df54721a196184741e8b2a88bd","cross_cats_sorted":["stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-08-19T16:26:21Z","title_canon_sha256":"309b79a59a2fec97ab32755abcb49391b4a038c189e345946c8677f37d8a1a0d"},"schema_version":"1.0","source":{"id":"2108.08773","kind":"arxiv","version":1}},"canonical_sha256":"3880be62419e421618c125b0653208835d36492a454ccb2b621748f897cf0999","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3880be62419e421618c125b0653208835d36492a454ccb2b621748f897cf0999","first_computed_at":"2026-07-05T03:07:13.406870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:13.406870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TzcjS4E9SN/ESQdFw7dNL5EFPp+rNQdcOlUfxROcyzvpUtpsDzkVPWBdQ5GcNMwgY24SPkA99WgkFVc+bqyPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:13.407348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.08773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d079613148542b4166a8d58f4175a53d2b67239c09d04807a2f5b59f09ebdb0","sha256:9048dd6e3484cef5f47c30d5e8e464a1c8ee990897c00b369fac987806dab101"],"state_sha256":"4e2b89819d5166a0ab1fe7b4d680e96db705f42c31e03d47c1c9f9797b481ffa"}