{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OTDRPO6CG25CERQJVFFZR5G2MJ","short_pith_number":"pith:OTDRPO6C","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"},"canonical_sha256":"74c717bbc236ba224609a94b98f4da627914c14042d6f960557908fee4512f78","source":{"kind":"arxiv","id":"2507.02628","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02628","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02628v2","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02628","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"OTDRPO6CG25C","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"OTDRPO6CG25CERQJ","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"OTDRPO6C","created_at":"2026-05-26T02:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OTDRPO6CG25CERQJVFFZR5G2MJ","target":"record","payload":{"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"},"canonical_sha256":"74c717bbc236ba224609a94b98f4da627914c14042d6f960557908fee4512f78","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"},"source_kind":"arxiv","source_id":"2507.02628","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"99VPRfw6GmQ9r9kdSfdaYiI7DoYqxLbH0ceMiYAgeZZZC9rhmpvj8wZtdpUye2iBqBBb/wcwG/fJheK7YdLIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:18:05.491523Z"},"content_sha256":"9eae9db5c1981999eb1a6a1f9fe690e525723d7ff920b57f6d85430550de5917","schema_version":"1.0","event_id":"sha256:9eae9db5c1981999eb1a6a1f9fe690e525723d7ff920b57f6d85430550de5917"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OTDRPO6CG25CERQJVFFZR5G2MJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mID5qDwH666EUTX4XNY7Ly5H2L86sef4FH4cv5LkTwUmcwzeFuAwQn5En9LmTHK4cTB66KlQP13kTH9IXze0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:18:05.492314Z"},"content_sha256":"6c0a585f2fb66537851e968e9659e663bb2ac0aa92d62f7605f3b1171abe06b5","schema_version":"1.0","event_id":"sha256:6c0a585f2fb66537851e968e9659e663bb2ac0aa92d62f7605f3b1171abe06b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/bundle.json","state_url":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T18:18:05Z","links":{"resolver":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ","bundle":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/bundle.json","state":"https://pith.science/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTDRPO6CG25CERQJVFFZR5G2MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OTDRPO6CG25CERQJVFFZR5G2MJ","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":"30f64db2a16b169706d4934a57b305717154db181172d8788b96be0a4c219292","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T13:54:50Z","title_canon_sha256":"f43c34cde78db65672a9483ce5968a12ceaebf5277bcb7d88c5902f4b82c90b5"},"schema_version":"1.0","source":{"id":"2507.02628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02628","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02628v2","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02628","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"OTDRPO6CG25C","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"OTDRPO6CG25CERQJ","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"OTDRPO6C","created_at":"2026-05-26T02:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:6c0a585f2fb66537851e968e9659e663bb2ac0aa92d62f7605f3b1171abe06b5","target":"graph","created_at":"2026-05-26T02:05:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.02628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Atai Ambus, Irena Girshovitz, Moni Shahar, Ran Gilad-Bachrach","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T13:54:50Z","title":"A Generative Approach for Semantic Auditing of Electronic Health Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02628","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":"sha256:9eae9db5c1981999eb1a6a1f9fe690e525723d7ff920b57f6d85430550de5917","target":"record","created_at":"2026-05-26T02:05:01Z","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":"30f64db2a16b169706d4934a57b305717154db181172d8788b96be0a4c219292","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T13:54:50Z","title_canon_sha256":"f43c34cde78db65672a9483ce5968a12ceaebf5277bcb7d88c5902f4b82c90b5"},"schema_version":"1.0","source":{"id":"2507.02628","kind":"arxiv","version":2}},"canonical_sha256":"74c717bbc236ba224609a94b98f4da627914c14042d6f960557908fee4512f78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74c717bbc236ba224609a94b98f4da627914c14042d6f960557908fee4512f78","first_computed_at":"2026-05-26T02:05:01.030072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:01.030072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"doKkQaZvsm/IVjT3ltrcsEPKnUwRWlA/YAi0VNuWuukk8+QQRUHXNfIujSwpW8ElJXmrUhcerhMw5NFzzXCGAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:01.030699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9eae9db5c1981999eb1a6a1f9fe690e525723d7ff920b57f6d85430550de5917","sha256:6c0a585f2fb66537851e968e9659e663bb2ac0aa92d62f7605f3b1171abe06b5"],"state_sha256":"7c8fdc70dceecb9bb2b6de457c648a94e8380d5f650783719a52fc6d601f5c0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEb+YJYTr0wuTN/3TquqjEyTQlTo4myp2olCnE4F2bkcfdb1RSXKuT6ExSbGgQZwWBLw2i3P9r2GKalhfHPuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:18:05.496497Z","bundle_sha256":"1dbb25af68c929b2309b259245f67d12d092d01807a62e5a6a7994f80514b3d6"}}