{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7JIUI4ZNRBVHP27FMBCHAA2RUJ","short_pith_number":"pith:7JIUI4ZN","canonical_record":{"source":{"id":"2506.12674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T00:57:48Z","cross_cats_sorted":[],"title_canon_sha256":"6eeb7b69495a82cccaccf3b9e7132564cdc500b0b8a109c635654d43d391b0eb","abstract_canon_sha256":"1a98aad596c114dbe0a0b0d50c8cd0bc3e63bda93233ecf9ff0ceb4aa8b7c6d0"},"schema_version":"1.0"},"canonical_sha256":"fa5144732d886a77ebe56044700351a26b007a245bf7ed57013603eb25606b4f","source":{"kind":"arxiv","id":"2506.12674","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12674","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12674v2","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12674","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"pith_short_12","alias_value":"7JIUI4ZNRBVH","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"pith_short_16","alias_value":"7JIUI4ZNRBVHP27F","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"pith_short_8","alias_value":"7JIUI4ZN","created_at":"2026-07-05T11:22:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7JIUI4ZNRBVHP27FMBCHAA2RUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T00:57:48Z","cross_cats_sorted":[],"title_canon_sha256":"6eeb7b69495a82cccaccf3b9e7132564cdc500b0b8a109c635654d43d391b0eb","abstract_canon_sha256":"1a98aad596c114dbe0a0b0d50c8cd0bc3e63bda93233ecf9ff0ceb4aa8b7c6d0"},"schema_version":"1.0"},"canonical_sha256":"fa5144732d886a77ebe56044700351a26b007a245bf7ed57013603eb25606b4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:42.176931Z","signature_b64":"CSo5NLKnd7PvSQYN/7w2d7Ieg72ko0NtzvEnvJDJNOxbpb0zmrIxcBkk+4V+01/af9oxhva06GBAhrZjLA7dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa5144732d886a77ebe56044700351a26b007a245bf7ed57013603eb25606b4f","last_reissued_at":"2026-07-05T11:22:42.176459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:42.176459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12674","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":"2026-07-05T11:22:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gICJBEBKtOlo+5Tors3UF54M9/GcYreuNrG6JIUTHpXLJxDsnfArFH2Gf8DTH1Ynf2euJOLOMqf4YVZ+Qpm4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:10:27.951351Z"},"content_sha256":"27c9dc8b6cc075b98439cfe3e1b0270db476ed3b3c7f778924bdbb61e6480f10","schema_version":"1.0","event_id":"sha256:27c9dc8b6cc075b98439cfe3e1b0270db476ed3b3c7f778924bdbb61e6480f10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7JIUI4ZNRBVHP27FMBCHAA2RUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Clinical Models with Pseudo Data for De-identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron J Chaise, Paul Landes, Ravi K Madduri, Tarak Nath Nandi","submitted_at":"2025-06-15T00:57:48Z","abstract_excerpt":"Many models are pretrained on redacted text for privacy reasons. Clinical foundation models are often trained on de-identified text, which uses special syntax (masked) text in place of protected health information. Even though these models have increased in popularity, there has been little effort in understanding the effects of training them on redacted text. In this work, we pretrain several encoder-only models on a dataset that contains redacted text and a version with replaced realistic pseudo text. We then fine-tuned models for the protected health information de-identification task and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12674","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/2506.12674/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":"2026-07-05T11:22:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vR99UpdLg9cqHdqkDWRdCG1oyxUd+dDbhqKbTKIhMSelPnQe2FxfHMKO4zbO/CAJmH5sFA3uFLHc3pVLawbcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:10:27.951867Z"},"content_sha256":"5da59bdab9b564f478a4860e221d801bc63b949d8a4d6040956ab6242b603075","schema_version":"1.0","event_id":"sha256:5da59bdab9b564f478a4860e221d801bc63b949d8a4d6040956ab6242b603075"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ/bundle.json","state_url":"https://pith.science/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ/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":"2026-08-07T17:10:27Z","links":{"resolver":"https://pith.science/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ","bundle":"https://pith.science/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ/bundle.json","state":"https://pith.science/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JIUI4ZNRBVHP27FMBCHAA2RUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7JIUI4ZNRBVHP27FMBCHAA2RUJ","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":"1a98aad596c114dbe0a0b0d50c8cd0bc3e63bda93233ecf9ff0ceb4aa8b7c6d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T00:57:48Z","title_canon_sha256":"6eeb7b69495a82cccaccf3b9e7132564cdc500b0b8a109c635654d43d391b0eb"},"schema_version":"1.0","source":{"id":"2506.12674","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12674","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12674v2","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12674","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"pith_short_12","alias_value":"7JIUI4ZNRBVH","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"pith_short_16","alias_value":"7JIUI4ZNRBVHP27F","created_at":"2026-07-05T11:22:42Z"},{"alias_kind":"pith_short_8","alias_value":"7JIUI4ZN","created_at":"2026-07-05T11:22:42Z"}],"graph_snapshots":[{"event_id":"sha256:5da59bdab9b564f478a4860e221d801bc63b949d8a4d6040956ab6242b603075","target":"graph","created_at":"2026-07-05T11:22:42Z","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/2506.12674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many models are pretrained on redacted text for privacy reasons. Clinical foundation models are often trained on de-identified text, which uses special syntax (masked) text in place of protected health information. Even though these models have increased in popularity, there has been little effort in understanding the effects of training them on redacted text. In this work, we pretrain several encoder-only models on a dataset that contains redacted text and a version with replaced realistic pseudo text. We then fine-tuned models for the protected health information de-identification task and s","authors_text":"Aaron J Chaise, Paul Landes, Ravi K Madduri, Tarak Nath Nandi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T00:57:48Z","title":"Enhancing Clinical Models with Pseudo Data for De-identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12674","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":"sha256:27c9dc8b6cc075b98439cfe3e1b0270db476ed3b3c7f778924bdbb61e6480f10","target":"record","created_at":"2026-07-05T11:22:42Z","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":"1a98aad596c114dbe0a0b0d50c8cd0bc3e63bda93233ecf9ff0ceb4aa8b7c6d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T00:57:48Z","title_canon_sha256":"6eeb7b69495a82cccaccf3b9e7132564cdc500b0b8a109c635654d43d391b0eb"},"schema_version":"1.0","source":{"id":"2506.12674","kind":"arxiv","version":2}},"canonical_sha256":"fa5144732d886a77ebe56044700351a26b007a245bf7ed57013603eb25606b4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa5144732d886a77ebe56044700351a26b007a245bf7ed57013603eb25606b4f","first_computed_at":"2026-07-05T11:22:42.176459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:42.176459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CSo5NLKnd7PvSQYN/7w2d7Ieg72ko0NtzvEnvJDJNOxbpb0zmrIxcBkk+4V+01/af9oxhva06GBAhrZjLA7dCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:42.176931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12674","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27c9dc8b6cc075b98439cfe3e1b0270db476ed3b3c7f778924bdbb61e6480f10","sha256:5da59bdab9b564f478a4860e221d801bc63b949d8a4d6040956ab6242b603075"],"state_sha256":"8d80bebc2c88d6560bba4cf0a9417551ae48023639306c58df9d0c8f137d73bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2duUuZ9PAOLEHstU3BFuKFt1jjGW6nYsNPEPSmaVxhesZbCa0bt9I9iWACmHCHQOGZy5XIVcs9w0V6h1jvcTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:10:27.955514Z","bundle_sha256":"dc861fd8e5df60702cc1988453e577e681debdbaa718153834ece61a54f0088e"}}