{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OQPONRCQZ6MVUDD7VDYTCZ3I7V","short_pith_number":"pith:OQPONRCQ","canonical_record":{"source":{"id":"2204.07056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:42:03Z","cross_cats_sorted":["stat.AP","stat.CO"],"title_canon_sha256":"d090b05bbfac6483fdd650e3436dfdcde77b2379abc4742ad4a60007e7f88ba0","abstract_canon_sha256":"41df171659181a11c1af0de4a836b67f45efe23015e2346b7cb1e7ff2384dfbc"},"schema_version":"1.0"},"canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","source":{"kind":"arxiv","id":"2204.07056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07056","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07056v1","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07056","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"OQPONRCQZ6MV","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"OQPONRCQZ6MVUDD7","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"OQPONRCQ","created_at":"2026-07-05T04:14:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OQPONRCQZ6MVUDD7VDYTCZ3I7V","target":"record","payload":{"canonical_record":{"source":{"id":"2204.07056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:42:03Z","cross_cats_sorted":["stat.AP","stat.CO"],"title_canon_sha256":"d090b05bbfac6483fdd650e3436dfdcde77b2379abc4742ad4a60007e7f88ba0","abstract_canon_sha256":"41df171659181a11c1af0de4a836b67f45efe23015e2346b7cb1e7ff2384dfbc"},"schema_version":"1.0"},"canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:48.835676Z","signature_b64":"BXTI5chqfKHmy4ypWqixSsAMN4tPPl/THFf+AVkPoHRmOlX/vCf3TSYc2QizlPrJUKY9POcMqpCbazzWa+p7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","last_reissued_at":"2026-07-05T04:14:48.835215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:48.835215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.07056","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":"2026-07-05T04:14:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSDvapsAhTQMrviSqIWGcuT2QM29ofDTWepTpMocV40wX7USrBkHtWwz+IeJQGNYoK4EysBOTE6csoh8w/WPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:17:16.504157Z"},"content_sha256":"42dd048f42e506e93c665b7b10b9bdefef75dc8650e97daf08f810c99d145f1c","schema_version":"1.0","event_id":"sha256:42dd048f42e506e93c665b7b10b9bdefef75dc8650e97daf08f810c99d145f1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OQPONRCQZ6MVUDD7VDYTCZ3I7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Evaluation Of Transformer Models For De-Identification Of Clinical Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"cs.CL","authors_text":"Christopher Meaney, Rahim Moineddin, Sumeet Kalia, Wali Hakimpour","submitted_at":"2022-03-25T19:42:03Z","abstract_excerpt":"Objective: To comparatively evaluate several transformer model architectures at identifying protected health information (PHI) in the i2b2/UTHealth 2014 clinical text de-identification challenge corpus.\n  Methods: The i2b2/UTHealth 2014 corpus contains N=1304 clinical notes obtained from N=296 patients. Using a transfer learning framework, we fine-tune several transformer model architectures on the corpus, including: BERT-base, BERT-large, ROBERTA-base, ROBERTA-large, ALBERT-base and ALBERT-xxlarge. During fine-tuning we vary the following model hyper-parameters: batch size, number training ep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07056","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/2204.07056/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":"2026-07-05T04:14:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RS1Kj6eQGZhkKWR/PLsrJHk0U4C9TgnIjS0KVvJhf/nd0PfAvFAjrs0C7cUFjSXDRtDMkC4koql/asLLxpUwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:17:16.504716Z"},"content_sha256":"e1e9c9d103c7c0dabeb99aeff055e4cfe416a72ac25a2c123b4a9d4cb417efb3","schema_version":"1.0","event_id":"sha256:e1e9c9d103c7c0dabeb99aeff055e4cfe416a72ac25a2c123b4a9d4cb417efb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/bundle.json","state_url":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/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":"2026-08-09T10:17:16Z","links":{"resolver":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V","bundle":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/bundle.json","state":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OQPONRCQZ6MVUDD7VDYTCZ3I7V","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":"41df171659181a11c1af0de4a836b67f45efe23015e2346b7cb1e7ff2384dfbc","cross_cats_sorted":["stat.AP","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:42:03Z","title_canon_sha256":"d090b05bbfac6483fdd650e3436dfdcde77b2379abc4742ad4a60007e7f88ba0"},"schema_version":"1.0","source":{"id":"2204.07056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07056","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07056v1","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07056","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"OQPONRCQZ6MV","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"OQPONRCQZ6MVUDD7","created_at":"2026-07-05T04:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"OQPONRCQ","created_at":"2026-07-05T04:14:48Z"}],"graph_snapshots":[{"event_id":"sha256:e1e9c9d103c7c0dabeb99aeff055e4cfe416a72ac25a2c123b4a9d4cb417efb3","target":"graph","created_at":"2026-07-05T04:14:48Z","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/2204.07056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Objective: To comparatively evaluate several transformer model architectures at identifying protected health information (PHI) in the i2b2/UTHealth 2014 clinical text de-identification challenge corpus.\n  Methods: The i2b2/UTHealth 2014 corpus contains N=1304 clinical notes obtained from N=296 patients. Using a transfer learning framework, we fine-tune several transformer model architectures on the corpus, including: BERT-base, BERT-large, ROBERTA-base, ROBERTA-large, ALBERT-base and ALBERT-xxlarge. During fine-tuning we vary the following model hyper-parameters: batch size, number training ep","authors_text":"Christopher Meaney, Rahim Moineddin, Sumeet Kalia, Wali Hakimpour","cross_cats":["stat.AP","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:42:03Z","title":"A Comparative Evaluation Of Transformer Models For De-Identification Of Clinical Text Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07056","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":"sha256:42dd048f42e506e93c665b7b10b9bdefef75dc8650e97daf08f810c99d145f1c","target":"record","created_at":"2026-07-05T04:14:48Z","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":"41df171659181a11c1af0de4a836b67f45efe23015e2346b7cb1e7ff2384dfbc","cross_cats_sorted":["stat.AP","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:42:03Z","title_canon_sha256":"d090b05bbfac6483fdd650e3436dfdcde77b2379abc4742ad4a60007e7f88ba0"},"schema_version":"1.0","source":{"id":"2204.07056","kind":"arxiv","version":1}},"canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","first_computed_at":"2026-07-05T04:14:48.835215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:48.835215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BXTI5chqfKHmy4ypWqixSsAMN4tPPl/THFf+AVkPoHRmOlX/vCf3TSYc2QizlPrJUKY9POcMqpCbazzWa+p7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:48.835676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42dd048f42e506e93c665b7b10b9bdefef75dc8650e97daf08f810c99d145f1c","sha256:e1e9c9d103c7c0dabeb99aeff055e4cfe416a72ac25a2c123b4a9d4cb417efb3"],"state_sha256":"cb173d1125cfcb2ac6b76919f07b32de5519b63925b24e91e597f42994e6d79d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbSEnj3Vnkd9T6kS+pINw0/UTXDwMWryaYumTO9VkaFBAtpE6/tL+5h3retAJ2cqj+VFC2vZixLJGR+i114YAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:17:16.509708Z","bundle_sha256":"7c31714be1462dc21149355d53131151b1cf1cd18309b63214692117be6c6a30"}}