{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:M4CQWK27OO4OTV43UYCTA3FKGM","short_pith_number":"pith:M4CQWK27","canonical_record":{"source":{"id":"2104.07762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T20:40:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b5a219f5745ee37873a0cc919f591874d3815ff9689bfd3f7e470df6fecdaae","abstract_canon_sha256":"c6bb857e91ca0e32a3912b506f2c261f562c119332cc5d375b8d90b547117764"},"schema_version":"1.0"},"canonical_sha256":"67050b2b5f73b8e9d79ba605306caa33226e23af051157dbdb9a586919d3e20b","source":{"kind":"arxiv","id":"2104.07762","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07762","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07762v2","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07762","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"M4CQWK27OO4O","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"M4CQWK27OO4OTV43","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"M4CQWK27","created_at":"2026-07-05T02:34:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:M4CQWK27OO4OTV43UYCTA3FKGM","target":"record","payload":{"canonical_record":{"source":{"id":"2104.07762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T20:40:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b5a219f5745ee37873a0cc919f591874d3815ff9689bfd3f7e470df6fecdaae","abstract_canon_sha256":"c6bb857e91ca0e32a3912b506f2c261f562c119332cc5d375b8d90b547117764"},"schema_version":"1.0"},"canonical_sha256":"67050b2b5f73b8e9d79ba605306caa33226e23af051157dbdb9a586919d3e20b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:21.625110Z","signature_b64":"D6/zGNcVpEhij2KSQ7WEd6yE/aPQO9DIQBod01T4BOvJk9ULUvuds028K64CXdXs4VwvUlnZ2itPWXxUEJvUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67050b2b5f73b8e9d79ba605306caa33226e23af051157dbdb9a586919d3e20b","last_reissued_at":"2026-07-05T02:34:21.624643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:21.624643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.07762","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":"2026-07-05T02:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4YN9pbiOPolC0AtwAKMLl2aFM5vY8xhro0RaBUM02X1HslVAe/IKAnS/kcBLj7xohfVhmeg0tBCbEByD0dECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:47:52.599356Z"},"content_sha256":"c9ed8d22e756713cae3ca3028a631730d6ff6b679052cd774086045335f4b928","schema_version":"1.0","event_id":"sha256:c9ed8d22e756713cae3ca3028a631730d6ff6b679052cd774086045335f4b928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:M4CQWK27OO4OTV43UYCTA3FKGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Byron C. Wallace, Eric Lehman, Karl Pichotta, Sarthak Jain, Yoav Goldberg","submitted_at":"2021-04-15T20:40:05Z","abstract_excerpt":"Large Transformers pretrained over clinical notes from Electronic Health Records (EHR) have afforded substantial gains in performance on predictive clinical tasks. The cost of training such models (and the necessity of data access to do so) coupled with their utility motivates parameter sharing, i.e., the release of pretrained models such as ClinicalBERT. While most efforts have used deidentified EHR, many researchers have access to large sets of sensitive, non-deidentified EHR with which they might train a BERT model (or similar). Would it be safe to release the weights of such a model if the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07762","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/2104.07762/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":"2026-07-05T02:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIbcQDyibW26Ib8OZKXiiMDzLR09VKfj5O2MHy5rS10nfhgVAuRO8MltzeoYXCcfWDXgRF4ykdZXQg0GBzNrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:47:52.600273Z"},"content_sha256":"2a4aabbe139072cd69183c3160c67544ea6c5a60366622673c2ccfad2dcc0bf8","schema_version":"1.0","event_id":"sha256:2a4aabbe139072cd69183c3160c67544ea6c5a60366622673c2ccfad2dcc0bf8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4CQWK27OO4OTV43UYCTA3FKGM/bundle.json","state_url":"https://pith.science/pith/M4CQWK27OO4OTV43UYCTA3FKGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4CQWK27OO4OTV43UYCTA3FKGM/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":"2026-08-17T23:47:52Z","links":{"resolver":"https://pith.science/pith/M4CQWK27OO4OTV43UYCTA3FKGM","bundle":"https://pith.science/pith/M4CQWK27OO4OTV43UYCTA3FKGM/bundle.json","state":"https://pith.science/pith/M4CQWK27OO4OTV43UYCTA3FKGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4CQWK27OO4OTV43UYCTA3FKGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M4CQWK27OO4OTV43UYCTA3FKGM","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":"c6bb857e91ca0e32a3912b506f2c261f562c119332cc5d375b8d90b547117764","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T20:40:05Z","title_canon_sha256":"3b5a219f5745ee37873a0cc919f591874d3815ff9689bfd3f7e470df6fecdaae"},"schema_version":"1.0","source":{"id":"2104.07762","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07762","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07762v2","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07762","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"M4CQWK27OO4O","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"M4CQWK27OO4OTV43","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"M4CQWK27","created_at":"2026-07-05T02:34:21Z"}],"graph_snapshots":[{"event_id":"sha256:2a4aabbe139072cd69183c3160c67544ea6c5a60366622673c2ccfad2dcc0bf8","target":"graph","created_at":"2026-07-05T02:34:21Z","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/2104.07762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Transformers pretrained over clinical notes from Electronic Health Records (EHR) have afforded substantial gains in performance on predictive clinical tasks. The cost of training such models (and the necessity of data access to do so) coupled with their utility motivates parameter sharing, i.e., the release of pretrained models such as ClinicalBERT. While most efforts have used deidentified EHR, many researchers have access to large sets of sensitive, non-deidentified EHR with which they might train a BERT model (or similar). Would it be safe to release the weights of such a model if the","authors_text":"Byron C. Wallace, Eric Lehman, Karl Pichotta, Sarthak Jain, Yoav Goldberg","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T20:40:05Z","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07762","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:c9ed8d22e756713cae3ca3028a631730d6ff6b679052cd774086045335f4b928","target":"record","created_at":"2026-07-05T02:34:21Z","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":"c6bb857e91ca0e32a3912b506f2c261f562c119332cc5d375b8d90b547117764","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T20:40:05Z","title_canon_sha256":"3b5a219f5745ee37873a0cc919f591874d3815ff9689bfd3f7e470df6fecdaae"},"schema_version":"1.0","source":{"id":"2104.07762","kind":"arxiv","version":2}},"canonical_sha256":"67050b2b5f73b8e9d79ba605306caa33226e23af051157dbdb9a586919d3e20b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67050b2b5f73b8e9d79ba605306caa33226e23af051157dbdb9a586919d3e20b","first_computed_at":"2026-07-05T02:34:21.624643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:21.624643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D6/zGNcVpEhij2KSQ7WEd6yE/aPQO9DIQBod01T4BOvJk9ULUvuds028K64CXdXs4VwvUlnZ2itPWXxUEJvUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:21.625110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07762","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9ed8d22e756713cae3ca3028a631730d6ff6b679052cd774086045335f4b928","sha256:2a4aabbe139072cd69183c3160c67544ea6c5a60366622673c2ccfad2dcc0bf8"],"state_sha256":"38271b3eacd9fe3774ddef2cc5386e26cc8145273d36c82c915fd8f5c31c2e19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WA41ijtuKrocEk21QKTUBFh2FxF+AUrQw+IgpxgtKU5St5Ys9QRcXEIuGWlLq+KHWN/KLzPHlSj8wQ46nZSlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:47:52.606247Z","bundle_sha256":"4eb6eb7a3abb208eb36e982f37e4441ee6bdc59e2cb84768b36adb50204a0fef"}}