{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:45SHVBPIKDLQFCVYJEECJMNOKD","short_pith_number":"pith:45SHVBPI","canonical_record":{"source":{"id":"2505.18380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T21:13:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fe3b6a9881ff470589790dff1cc899918c1b12245c9721ed0981b3177923539","abstract_canon_sha256":"0a0153400c944d5bf1e110117c455d7a549cdb9e408454e990089348c6db038b"},"schema_version":"1.0"},"canonical_sha256":"e7647a85e850d7028ab8490824b1ae50c4533f3962ab7844b051ab9fe4b86da9","source":{"kind":"arxiv","id":"2505.18380","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18380","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18380v2","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18380","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"45SHVBPIKDLQ","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"45SHVBPIKDLQFCVY","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"45SHVBPI","created_at":"2026-07-05T11:42:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:45SHVBPIKDLQFCVYJEECJMNOKD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T21:13:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fe3b6a9881ff470589790dff1cc899918c1b12245c9721ed0981b3177923539","abstract_canon_sha256":"0a0153400c944d5bf1e110117c455d7a549cdb9e408454e990089348c6db038b"},"schema_version":"1.0"},"canonical_sha256":"e7647a85e850d7028ab8490824b1ae50c4533f3962ab7844b051ab9fe4b86da9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:54.529421Z","signature_b64":"f6eqlylm0AokkQGlrpdpQUw+B0+DNNykGK+4Jm1S3/vSnpCqf6fY64eAOp3zBpQHMp4vry45Q3HpwGysI4lSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7647a85e850d7028ab8490824b1ae50c4533f3962ab7844b051ab9fe4b86da9","last_reissued_at":"2026-07-05T11:42:54.528934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:54.528934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18380","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":"2026-07-05T11:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/O8D+goWJ0SXmVX9xajkJNiwB9m2NNQ0QT4fSiIwO8gQZFvzjsCgPzTIuYbtGnMwisrogXqG2w97fmUM/v1vCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:36:55.565172Z"},"content_sha256":"25f22f50e183f8301d3d7be2d3f0749195a6c4539d661d5cb6ae1ca2a210bdb3","schema_version":"1.0","event_id":"sha256:25f22f50e183f8301d3d7be2d3f0749195a6c4539d661d5cb6ae1ca2a210bdb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:45SHVBPIKDLQFCVYJEECJMNOKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Charlotte Dzialo, Irfan Bulu, Jangwon Kim, Krishnaram Kenthapadi, Praphul Singh, Sri Gadde, Sumana Srivatsa","submitted_at":"2025-05-23T21:13:18Z","abstract_excerpt":"Ensuring clinical data privacy while preserving utility is critical for AI-driven healthcare and data analytics. Existing de-identification (De-ID) methods, including rule-based techniques, deep learning models, and large language models (LLMs), often suffer from recall errors, limited generalization, and inefficiencies, limiting their real-world applicability. We propose a fully automated, multi-modal framework, RedactOR for de-identifying structured and unstructured electronic health records, including clinical audio records. Our framework employs cost-efficient De-ID strategies, including i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18380","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/2505.18380/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":"2026-07-05T11:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3J7fKsp0RIFj05S61dE+o7VXIcA/7/mMHYvyz5ju4vPUcmcb6h43Uk3eleUyWVJURon0Q5gfVgo527tEwPQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:36:55.566068Z"},"content_sha256":"be01bb52ddafbcdc98b98b42077ce6e368fe34f24a01b30478027c2733dc01e4","schema_version":"1.0","event_id":"sha256:be01bb52ddafbcdc98b98b42077ce6e368fe34f24a01b30478027c2733dc01e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45SHVBPIKDLQFCVYJEECJMNOKD/bundle.json","state_url":"https://pith.science/pith/45SHVBPIKDLQFCVYJEECJMNOKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45SHVBPIKDLQFCVYJEECJMNOKD/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":"2026-08-08T15:36:55Z","links":{"resolver":"https://pith.science/pith/45SHVBPIKDLQFCVYJEECJMNOKD","bundle":"https://pith.science/pith/45SHVBPIKDLQFCVYJEECJMNOKD/bundle.json","state":"https://pith.science/pith/45SHVBPIKDLQFCVYJEECJMNOKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45SHVBPIKDLQFCVYJEECJMNOKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:45SHVBPIKDLQFCVYJEECJMNOKD","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":"0a0153400c944d5bf1e110117c455d7a549cdb9e408454e990089348c6db038b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T21:13:18Z","title_canon_sha256":"6fe3b6a9881ff470589790dff1cc899918c1b12245c9721ed0981b3177923539"},"schema_version":"1.0","source":{"id":"2505.18380","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18380","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18380v2","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18380","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"45SHVBPIKDLQ","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"45SHVBPIKDLQFCVY","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"45SHVBPI","created_at":"2026-07-05T11:42:54Z"}],"graph_snapshots":[{"event_id":"sha256:be01bb52ddafbcdc98b98b42077ce6e368fe34f24a01b30478027c2733dc01e4","target":"graph","created_at":"2026-07-05T11:42:54Z","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/2505.18380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring clinical data privacy while preserving utility is critical for AI-driven healthcare and data analytics. Existing de-identification (De-ID) methods, including rule-based techniques, deep learning models, and large language models (LLMs), often suffer from recall errors, limited generalization, and inefficiencies, limiting their real-world applicability. We propose a fully automated, multi-modal framework, RedactOR for de-identifying structured and unstructured electronic health records, including clinical audio records. Our framework employs cost-efficient De-ID strategies, including i","authors_text":"Charlotte Dzialo, Irfan Bulu, Jangwon Kim, Krishnaram Kenthapadi, Praphul Singh, Sri Gadde, Sumana Srivatsa","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T21:13:18Z","title":"RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18380","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":"sha256:25f22f50e183f8301d3d7be2d3f0749195a6c4539d661d5cb6ae1ca2a210bdb3","target":"record","created_at":"2026-07-05T11:42:54Z","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":"0a0153400c944d5bf1e110117c455d7a549cdb9e408454e990089348c6db038b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T21:13:18Z","title_canon_sha256":"6fe3b6a9881ff470589790dff1cc899918c1b12245c9721ed0981b3177923539"},"schema_version":"1.0","source":{"id":"2505.18380","kind":"arxiv","version":2}},"canonical_sha256":"e7647a85e850d7028ab8490824b1ae50c4533f3962ab7844b051ab9fe4b86da9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7647a85e850d7028ab8490824b1ae50c4533f3962ab7844b051ab9fe4b86da9","first_computed_at":"2026-07-05T11:42:54.528934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:54.528934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f6eqlylm0AokkQGlrpdpQUw+B0+DNNykGK+4Jm1S3/vSnpCqf6fY64eAOp3zBpQHMp4vry45Q3HpwGysI4lSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:54.529421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18380","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25f22f50e183f8301d3d7be2d3f0749195a6c4539d661d5cb6ae1ca2a210bdb3","sha256:be01bb52ddafbcdc98b98b42077ce6e368fe34f24a01b30478027c2733dc01e4"],"state_sha256":"7789c29be7731c12af4aa646a25946f3231c1293008258ca80371744502b79a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHa8PuAzkSKnEC//+FXY60JvEj04Poqs1w+9o5DFO6py3+fCn72DOJQhCA5fMaDKhGnBoW0WQI6RlwU2mncNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:36:55.573739Z","bundle_sha256":"a5b2abb28e6623490bd0ada835c332e140f80ed0786d9809baaf2bf8d08a0264"}}