{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JM2RU62O3R6X75ZN4NSNALPKXS","short_pith_number":"pith:JM2RU62O","canonical_record":{"source":{"id":"2506.08231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T20:59:16Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"371c40e5dd5ac309b77f3043529e8599620fc9b2c3fbef20f0641fb3016fc65a","abstract_canon_sha256":"a0bc60d166afe525bd7f6ee50b3651add4e89c7134649f013305dd5d5b77263c"},"schema_version":"1.0"},"canonical_sha256":"4b351a7b4edc7d7ff72de364d02deabc8641ef534b7ebd1269fb0806a323fbce","source":{"kind":"arxiv","id":"2506.08231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08231","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08231v1","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08231","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"JM2RU62O3R6X","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"JM2RU62O3R6X75ZN","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"JM2RU62O","created_at":"2026-07-05T11:18:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JM2RU62O3R6X75ZN4NSNALPKXS","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T20:59:16Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"371c40e5dd5ac309b77f3043529e8599620fc9b2c3fbef20f0641fb3016fc65a","abstract_canon_sha256":"a0bc60d166afe525bd7f6ee50b3651add4e89c7134649f013305dd5d5b77263c"},"schema_version":"1.0"},"canonical_sha256":"4b351a7b4edc7d7ff72de364d02deabc8641ef534b7ebd1269fb0806a323fbce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:46.597537Z","signature_b64":"MqsSBGsbT2AHN7yYCg1pyAsfbZ4KkQWeLiRnforGIHc8yIvNgcRDY8MitKHvHdhpby/iYCTfokgA6QONdy03Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b351a7b4edc7d7ff72de364d02deabc8641ef534b7ebd1269fb0806a323fbce","last_reissued_at":"2026-07-05T11:18:46.597042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:46.597042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08231","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eIcu5JsOtSirTlwLqaYDgaU0M2qMrFkuSrlNdl6VGjwMLO2l/Z8bFaxMhAdOTnfvp6GvkQpyh45JxPnoJwrvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:02:46.137079Z"},"content_sha256":"a5bd4a0c30efa3bf27a25821be258aac8d23b9b67d309dfe8f96e372a8499e0a","schema_version":"1.0","event_id":"sha256:a5bd4a0c30efa3bf27a25821be258aac8d23b9b67d309dfe8f96e372a8499e0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JM2RU62O3R6X75ZN4NSNALPKXS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensuring Reliability of Curated EHR-Derived Data: The Validation of Accuracy for LLM/ML-Extracted Information and Data (VALID) Framework","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Aaron B. Cohen, Blythe Adamson, Erin Fidyk, Farhad Khan, Kathi Seidl-Rathkopf, Lauren Dyson, Megan W. Hildner, Melissa Estevez, Nisha Singh, Olive Mbah, Qianyu Yuan","submitted_at":"2025-06-09T20:59:16Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to extract clinical data from electronic health records (EHRs), offering significant improvements in scalability and efficiency for real-world data (RWD) curation in oncology. However, the adoption of LLMs introduces new challenges in ensuring the reliability, accuracy, and fairness of extracted data, which are essential for research, regulatory, and clinical applications. Existing quality assurance frameworks for RWD and artificial intelligence do not fully address the unique error modes and complexities associated with LLM-extracted data. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08231","kind":"arxiv","version":1},"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/2506.08231/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":"2026-07-05T11:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEFXPbTsmwucdbqujKa6rKMULGFHucOwKFfRM79PHmtn2FnwKha2pgGFEdYND5BDrPAHJCj7EMjH2nQhXRZsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:02:46.137707Z"},"content_sha256":"ef635ed130a3fe357f4ccc076c47e07eca18c9be1e95c7a37120ac7db5004c36","schema_version":"1.0","event_id":"sha256:ef635ed130a3fe357f4ccc076c47e07eca18c9be1e95c7a37120ac7db5004c36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JM2RU62O3R6X75ZN4NSNALPKXS/bundle.json","state_url":"https://pith.science/pith/JM2RU62O3R6X75ZN4NSNALPKXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JM2RU62O3R6X75ZN4NSNALPKXS/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":"2026-08-10T07:02:46Z","links":{"resolver":"https://pith.science/pith/JM2RU62O3R6X75ZN4NSNALPKXS","bundle":"https://pith.science/pith/JM2RU62O3R6X75ZN4NSNALPKXS/bundle.json","state":"https://pith.science/pith/JM2RU62O3R6X75ZN4NSNALPKXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JM2RU62O3R6X75ZN4NSNALPKXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JM2RU62O3R6X75ZN4NSNALPKXS","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":"a0bc60d166afe525bd7f6ee50b3651add4e89c7134649f013305dd5d5b77263c","cross_cats_sorted":["cs.AI","cs.PF"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T20:59:16Z","title_canon_sha256":"371c40e5dd5ac309b77f3043529e8599620fc9b2c3fbef20f0641fb3016fc65a"},"schema_version":"1.0","source":{"id":"2506.08231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08231","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08231v1","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08231","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"JM2RU62O3R6X","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"JM2RU62O3R6X75ZN","created_at":"2026-07-05T11:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"JM2RU62O","created_at":"2026-07-05T11:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:ef635ed130a3fe357f4ccc076c47e07eca18c9be1e95c7a37120ac7db5004c36","target":"graph","created_at":"2026-07-05T11:18:46Z","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/2506.08231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used to extract clinical data from electronic health records (EHRs), offering significant improvements in scalability and efficiency for real-world data (RWD) curation in oncology. However, the adoption of LLMs introduces new challenges in ensuring the reliability, accuracy, and fairness of extracted data, which are essential for research, regulatory, and clinical applications. Existing quality assurance frameworks for RWD and artificial intelligence do not fully address the unique error modes and complexities associated with LLM-extracted data. In","authors_text":"Aaron B. Cohen, Blythe Adamson, Erin Fidyk, Farhad Khan, Kathi Seidl-Rathkopf, Lauren Dyson, Megan W. Hildner, Melissa Estevez, Nisha Singh, Olive Mbah, Qianyu Yuan","cross_cats":["cs.AI","cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T20:59:16Z","title":"Ensuring Reliability of Curated EHR-Derived Data: The Validation of Accuracy for LLM/ML-Extracted Information and Data (VALID) Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08231","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:a5bd4a0c30efa3bf27a25821be258aac8d23b9b67d309dfe8f96e372a8499e0a","target":"record","created_at":"2026-07-05T11:18:46Z","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":"a0bc60d166afe525bd7f6ee50b3651add4e89c7134649f013305dd5d5b77263c","cross_cats_sorted":["cs.AI","cs.PF"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T20:59:16Z","title_canon_sha256":"371c40e5dd5ac309b77f3043529e8599620fc9b2c3fbef20f0641fb3016fc65a"},"schema_version":"1.0","source":{"id":"2506.08231","kind":"arxiv","version":1}},"canonical_sha256":"4b351a7b4edc7d7ff72de364d02deabc8641ef534b7ebd1269fb0806a323fbce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b351a7b4edc7d7ff72de364d02deabc8641ef534b7ebd1269fb0806a323fbce","first_computed_at":"2026-07-05T11:18:46.597042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:46.597042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MqsSBGsbT2AHN7yYCg1pyAsfbZ4KkQWeLiRnforGIHc8yIvNgcRDY8MitKHvHdhpby/iYCTfokgA6QONdy03Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:46.597537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5bd4a0c30efa3bf27a25821be258aac8d23b9b67d309dfe8f96e372a8499e0a","sha256:ef635ed130a3fe357f4ccc076c47e07eca18c9be1e95c7a37120ac7db5004c36"],"state_sha256":"d84e2f0fc2ca811e988e2ce8b9eddd2cbf4a1addac48b6b029c773e1bbaf2e7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ajd3kFnSDXV0kVGb3R/uERAe4fQHG6D1ZXziHTh1MJ6WUFjVWz+6RK8cFs0SSzheQ4A7yYhYr2OFoeexHPt2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:02:46.143290Z","bundle_sha256":"c3c929e50e38ef31eb539d4ef10555ac8fa6a8209226d3cb3fe7d3c0faff7e4a"}}