{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OTDRPO6CG25CERQJVFFZR5G2MJ","short_pith_number":"pith:OTDRPO6C","schema_version":"1.0","canonical_sha256":"74c717bbc236ba224609a94b98f4da627914c14042d6f960557908fee4512f78","source":{"kind":"arxiv","id":"2507.02628","version":2},"attestation_state":"computed","paper":{"title":"A Generative Approach for Semantic Auditing of Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Atai Ambus, Irena Girshovitz, Moni Shahar, Ran Gilad-Bachrach","submitted_at":"2025-07-03T13:54:50Z","abstract_excerpt":"The reliability of clinical artificial intelligence (AI) depends on high-quality data, yet Electronic Health Records are often inconsistent with existing scientific knowledge. Current quality assessments are limited: they either focus on syntax or rely on labor-intensive manual rules to capture semantic nuances. To overcome these scalability barriers, we propose Medical Data Pecking, a methodology that adopts software unit testing principles for medical data validation. It introduces Semantic Data Coverage, employing Large Language Models to generate context-aware tests that \"peck\" for inconsi"},"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":"2507.02628","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T13:54:50Z","cross_cats_sorted":[],"title_canon_sha256":"f43c34cde78db65672a9483ce5968a12ceaebf5277bcb7d88c5902f4b82c90b5","abstract_canon_sha256":"30f64db2a16b169706d4934a57b305717154db181172d8788b96be0a4c219292"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:01.030699Z","signature_b64":"doKkQaZvsm/IVjT3ltrcsEPKnUwRWlA/YAi0VNuWuukk8+QQRUHXNfIujSwpW8ElJXmrUhcerhMw5NFzzXCGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74c717bbc236ba224609a94b98f4da627914c14042d6f960557908fee4512f78","last_reissued_at":"2026-05-26T02:05:01.030072Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:01.030072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generative Approach for Semantic Auditing of Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Atai Ambus, Irena Girshovitz, Moni Shahar, Ran Gilad-Bachrach","submitted_at":"2025-07-03T13:54:50Z","abstract_excerpt":"The reliability of clinical artificial intelligence (AI) depends on high-quality data, yet Electronic Health Records are often inconsistent with existing scientific knowledge. Current quality assessments are limited: they either focus on syntax or rely on labor-intensive manual rules to capture semantic nuances. To overcome these scalability barriers, we propose Medical Data Pecking, a methodology that adopts software unit testing principles for medical data validation. It introduces Semantic Data Coverage, employing Large Language Models to generate context-aware tests that \"peck\" for inconsi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02628","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/2507.02628/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":"2507.02628","created_at":"2026-05-26T02:05:01.030182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02628v2","created_at":"2026-05-26T02:05:01.030182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02628","created_at":"2026-05-26T02:05:01.030182+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTDRPO6CG25C","created_at":"2026-05-26T02:05:01.030182+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTDRPO6CG25CERQJ","created_at":"2026-05-26T02:05:01.030182+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTDRPO6C","created_at":"2026-05-26T02:05:01.030182+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/OTDRPO6CG25CERQJVFFZR5G2MJ","json":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ.json","graph_json":"https://pith.science/api/pith-number/OTDRPO6CG25CERQJVFFZR5G2MJ/graph.json","events_json":"https://pith.science/api/pith-number/OTDRPO6CG25CERQJVFFZR5G2MJ/events.json","paper":"https://pith.science/paper/OTDRPO6C"},"agent_actions":{"view_html":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ","download_json":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ.json","view_paper":"https://pith.science/paper/OTDRPO6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02628&json=true","fetch_graph":"https://pith.science/api/pith-number/OTDRPO6CG25CERQJVFFZR5G2MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OTDRPO6CG25CERQJVFFZR5G2MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/action/storage_attestation","attest_author":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/action/author_attestation","sign_citation":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/action/citation_signature","submit_replication":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/action/replication_record"}},"created_at":"2026-05-26T02:05:01.030182+00:00","updated_at":"2026-05-26T02:05:01.030182+00:00"}