{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NZNNT2R5GUIDEVLWU7XVB4SWJP","short_pith_number":"pith:NZNNT2R5","canonical_record":{"source":{"id":"1904.03323","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-06T00:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"7249ceb8dea0dd9c5eeb21f51eda3144b0e07d8eb4ea6a707795336ee70b0687","abstract_canon_sha256":"a7e7248fb5802a23b2ff6074e466170895df29ee791b29fa58271824f3411660"},"schema_version":"1.0"},"canonical_sha256":"6e5ad9ea3d3510325576a7ef50f2564bcb06be465f7f31fa06db7278bbb5ab38","source":{"kind":"arxiv","id":"1904.03323","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03323","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03323v3","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03323","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"NZNNT2R5GUID","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NZNNT2R5GUIDEVLW","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NZNNT2R5","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NZNNT2R5GUIDEVLWU7XVB4SWJP","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03323","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-06T00:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"7249ceb8dea0dd9c5eeb21f51eda3144b0e07d8eb4ea6a707795336ee70b0687","abstract_canon_sha256":"a7e7248fb5802a23b2ff6074e466170895df29ee791b29fa58271824f3411660"},"schema_version":"1.0"},"canonical_sha256":"6e5ad9ea3d3510325576a7ef50f2564bcb06be465f7f31fa06db7278bbb5ab38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:48.237087Z","signature_b64":"on/yK+pcH0fU9PZMp5b5UmMJ2SmuyTUzWpQCdKIKcGrtM7/Gi+EutcciTwKqtih99ovArgnWRgu5bQxaK8imCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5ad9ea3d3510325576a7ef50f2564bcb06be465f7f31fa06db7278bbb5ab38","last_reissued_at":"2026-05-17T23:42:48.236551Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:48.236551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03323","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYjv1PUx9FuJtvkLv5ja8jyVL/73iheR0SNIUswx7GHM8WKlvKH6KBMepA7HtQj8FFy0hvArjtAdKumLk9Z4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:25:50.462150Z"},"content_sha256":"11b1f447abc98b4aea973d98c923f61eebc7f397c5a12b8220930821ed2b52ba","schema_version":"1.0","event_id":"sha256:11b1f447abc98b4aea973d98c923f61eebc7f397c5a12b8220930821ed2b52ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NZNNT2R5GUIDEVLWU7XVB4SWJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Publicly Available Clinical BERT Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Jin, Emily Alsentzer, John R. Murphy, Matthew B. A. McDermott, Tristan Naumann, Wei-Hung Weng, Willie Boag","submitted_at":"2019-04-06T00:34:39Z","abstract_excerpt":"Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been minimally explored on specialty corpora, such as clinical text; moreover, in the clinical domain, no publicly-available pre-trained BERT models yet exist. In this work, we address this need by exploring and releasing BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically. We demonstrate that using a domain-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03323","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:42:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwawPIKc3inj6aV/DfJlhlEujiWa9Aq051WL3wQpgPYfy4xcPMVTMx2OxiUtUBSMb5DLgUnbEqAwv7xB//HpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:25:50.462513Z"},"content_sha256":"ff6d435707e9da76896263307d3b805396a1ca7e4e1e10e891d721965ba405a2","schema_version":"1.0","event_id":"sha256:ff6d435707e9da76896263307d3b805396a1ca7e4e1e10e891d721965ba405a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP/bundle.json","state_url":"https://pith.science/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP/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":"2026-06-02T20:25:50Z","links":{"resolver":"https://pith.science/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP","bundle":"https://pith.science/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP/bundle.json","state":"https://pith.science/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZNNT2R5GUIDEVLWU7XVB4SWJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NZNNT2R5GUIDEVLWU7XVB4SWJP","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":"a7e7248fb5802a23b2ff6074e466170895df29ee791b29fa58271824f3411660","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-06T00:34:39Z","title_canon_sha256":"7249ceb8dea0dd9c5eeb21f51eda3144b0e07d8eb4ea6a707795336ee70b0687"},"schema_version":"1.0","source":{"id":"1904.03323","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03323","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03323v3","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03323","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"NZNNT2R5GUID","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NZNNT2R5GUIDEVLW","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NZNNT2R5","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:ff6d435707e9da76896263307d3b805396a1ca7e4e1e10e891d721965ba405a2","target":"graph","created_at":"2026-05-17T23:42:48Z","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"},"paper":{"abstract_excerpt":"Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been minimally explored on specialty corpora, such as clinical text; moreover, in the clinical domain, no publicly-available pre-trained BERT models yet exist. In this work, we address this need by exploring and releasing BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically. We demonstrate that using a domain-","authors_text":"Di Jin, Emily Alsentzer, John R. Murphy, Matthew B. A. McDermott, Tristan Naumann, Wei-Hung Weng, Willie Boag","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-06T00:34:39Z","title":"Publicly Available Clinical BERT Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03323","kind":"arxiv","version":3},"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":"sha256:11b1f447abc98b4aea973d98c923f61eebc7f397c5a12b8220930821ed2b52ba","target":"record","created_at":"2026-05-17T23:42:48Z","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":"a7e7248fb5802a23b2ff6074e466170895df29ee791b29fa58271824f3411660","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-06T00:34:39Z","title_canon_sha256":"7249ceb8dea0dd9c5eeb21f51eda3144b0e07d8eb4ea6a707795336ee70b0687"},"schema_version":"1.0","source":{"id":"1904.03323","kind":"arxiv","version":3}},"canonical_sha256":"6e5ad9ea3d3510325576a7ef50f2564bcb06be465f7f31fa06db7278bbb5ab38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e5ad9ea3d3510325576a7ef50f2564bcb06be465f7f31fa06db7278bbb5ab38","first_computed_at":"2026-05-17T23:42:48.236551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:48.236551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"on/yK+pcH0fU9PZMp5b5UmMJ2SmuyTUzWpQCdKIKcGrtM7/Gi+EutcciTwKqtih99ovArgnWRgu5bQxaK8imCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:48.237087Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03323","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11b1f447abc98b4aea973d98c923f61eebc7f397c5a12b8220930821ed2b52ba","sha256:ff6d435707e9da76896263307d3b805396a1ca7e4e1e10e891d721965ba405a2"],"state_sha256":"f295fe34604a481fbe522248a0251ed92a9563bf894c07794053cb94fcb9edc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDRGPi99S14SO5BSvM5uaRi5IVPWhmdIPF1lhSVSyXIHnogF3n3+oJSwR4G0rzP9IX7/1fCUsqTxthFgeeGPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:25:50.464442Z","bundle_sha256":"4fca4a7d4013c738d3be7902c3abfe32f8ce97b6a2a720f655263fc4929dc225"}}