{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SQD5P2VZSNHSQ6VMYJFUWGYC3I","short_pith_number":"pith:SQD5P2VZ","canonical_record":{"source":{"id":"2411.18940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T06:12:28Z","cross_cats_sorted":[],"title_canon_sha256":"1f0ba3c586e4a5cb5cd43d5ba3c55f61b85b32158addd3b7dfaf3cb705b653d6","abstract_canon_sha256":"5c11523e8bd312c8fe0d5c23eb266551074e6fe73833aa5dc9d65199ea7d81cb"},"schema_version":"1.0"},"canonical_sha256":"9407d7eab9934f287aacc24b4b1b02da1327a5b8ada365f967ce0bedf09a42a7","source":{"kind":"arxiv","id":"2411.18940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18940","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18940v1","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18940","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_12","alias_value":"SQD5P2VZSNHS","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_16","alias_value":"SQD5P2VZSNHSQ6VM","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_8","alias_value":"SQD5P2VZ","created_at":"2026-07-05T09:41:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SQD5P2VZSNHSQ6VMYJFUWGYC3I","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T06:12:28Z","cross_cats_sorted":[],"title_canon_sha256":"1f0ba3c586e4a5cb5cd43d5ba3c55f61b85b32158addd3b7dfaf3cb705b653d6","abstract_canon_sha256":"5c11523e8bd312c8fe0d5c23eb266551074e6fe73833aa5dc9d65199ea7d81cb"},"schema_version":"1.0"},"canonical_sha256":"9407d7eab9934f287aacc24b4b1b02da1327a5b8ada365f967ce0bedf09a42a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:54.340002Z","signature_b64":"WUsOj5O4VsKifmPrnROyxCUQ9OZNYaJrHZGZf+n5llNcrPc0OlwgxMq9p0/PB+L82KnoW0a4kzX5EdhAoRGWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9407d7eab9934f287aacc24b4b1b02da1327a5b8ada365f967ce0bedf09a42a7","last_reissued_at":"2026-07-05T09:41:54.339595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:54.339595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18940","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":"2026-07-05T09:41:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1/U+sUyEykGJL56S738f6kwagDsWn2Ov9ZJoxk8upvIHT7c4e9Hb+FjiWL0zSwscIgAjCJWsERSxB7AaUBJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:45:07.118292Z"},"content_sha256":"9a0973c60e1d73c24122199b1cfe8a7a0cebb3fbc431db8502cb5fe8f2ab8d86","schema_version":"1.0","event_id":"sha256:9a0973c60e1d73c24122199b1cfe8a7a0cebb3fbc431db8502cb5fe8f2ab8d86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SQD5P2VZSNHSQ6VMYJFUWGYC3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rephrasing Electronic Health Records for Pretraining Clinical Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Nguyen, Jinghui Liu","submitted_at":"2024-11-28T06:12:28Z","abstract_excerpt":"Clinical language models are important for many applications in healthcare, but their development depends on access to extensive clinical text for pretraining. However, obtaining clinical notes from electronic health records (EHRs) at scale is challenging due to patient privacy concerns. In this study, we rephrase existing clinical notes using LLMs to generate synthetic pretraining corpora, drawing inspiration from previous work on rephrasing web data. We examine four popular small-sized LLMs (<10B) to create synthetic clinical text to pretrain both decoder-based and encoder-based language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18940","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/2411.18940/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":"2026-07-05T09:41:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cbizJ0KP44CqOSfaIV7x1iM2tADuOIOQVEO85Ztk07Uyq/o1XlNQ85aSS5E4kkHluSppwiCfwk5z3ZiDt+mlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:45:07.118880Z"},"content_sha256":"9b6e97d3fe6690e2f7b63e423890d0b2070e88799b44028876803ce218b09ac5","schema_version":"1.0","event_id":"sha256:9b6e97d3fe6690e2f7b63e423890d0b2070e88799b44028876803ce218b09ac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I/bundle.json","state_url":"https://pith.science/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I/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":"2026-08-21T15:45:07Z","links":{"resolver":"https://pith.science/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I","bundle":"https://pith.science/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I/bundle.json","state":"https://pith.science/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQD5P2VZSNHSQ6VMYJFUWGYC3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SQD5P2VZSNHSQ6VMYJFUWGYC3I","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":"5c11523e8bd312c8fe0d5c23eb266551074e6fe73833aa5dc9d65199ea7d81cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T06:12:28Z","title_canon_sha256":"1f0ba3c586e4a5cb5cd43d5ba3c55f61b85b32158addd3b7dfaf3cb705b653d6"},"schema_version":"1.0","source":{"id":"2411.18940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18940","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18940v1","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18940","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_12","alias_value":"SQD5P2VZSNHS","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_16","alias_value":"SQD5P2VZSNHSQ6VM","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_8","alias_value":"SQD5P2VZ","created_at":"2026-07-05T09:41:54Z"}],"graph_snapshots":[{"event_id":"sha256:9b6e97d3fe6690e2f7b63e423890d0b2070e88799b44028876803ce218b09ac5","target":"graph","created_at":"2026-07-05T09:41:54Z","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/2411.18940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical language models are important for many applications in healthcare, but their development depends on access to extensive clinical text for pretraining. However, obtaining clinical notes from electronic health records (EHRs) at scale is challenging due to patient privacy concerns. In this study, we rephrase existing clinical notes using LLMs to generate synthetic pretraining corpora, drawing inspiration from previous work on rephrasing web data. We examine four popular small-sized LLMs (<10B) to create synthetic clinical text to pretrain both decoder-based and encoder-based language mod","authors_text":"Anthony Nguyen, Jinghui Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T06:12:28Z","title":"Rephrasing Electronic Health Records for Pretraining Clinical Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18940","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":"sha256:9a0973c60e1d73c24122199b1cfe8a7a0cebb3fbc431db8502cb5fe8f2ab8d86","target":"record","created_at":"2026-07-05T09:41:54Z","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":"5c11523e8bd312c8fe0d5c23eb266551074e6fe73833aa5dc9d65199ea7d81cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T06:12:28Z","title_canon_sha256":"1f0ba3c586e4a5cb5cd43d5ba3c55f61b85b32158addd3b7dfaf3cb705b653d6"},"schema_version":"1.0","source":{"id":"2411.18940","kind":"arxiv","version":1}},"canonical_sha256":"9407d7eab9934f287aacc24b4b1b02da1327a5b8ada365f967ce0bedf09a42a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9407d7eab9934f287aacc24b4b1b02da1327a5b8ada365f967ce0bedf09a42a7","first_computed_at":"2026-07-05T09:41:54.339595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:54.339595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WUsOj5O4VsKifmPrnROyxCUQ9OZNYaJrHZGZf+n5llNcrPc0OlwgxMq9p0/PB+L82KnoW0a4kzX5EdhAoRGWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:54.340002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a0973c60e1d73c24122199b1cfe8a7a0cebb3fbc431db8502cb5fe8f2ab8d86","sha256:9b6e97d3fe6690e2f7b63e423890d0b2070e88799b44028876803ce218b09ac5"],"state_sha256":"d01d5ef09c3e00647ff2bc97afabfc2ed9d598b197b19d08467ec6902b88bd17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sQ609KDErpInbFAo8hjAMdjKtcNNCSicekAETlxxRWVyBg37cUNNduh3Fst9utgXUCzTpzcTs1C91zyEKV38DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:45:07.122874Z","bundle_sha256":"4a4a066c4e882b8b0e56987c320e7626fde0c73e1dce05ca9e84775233a810f4"}}