{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RW7UM2Z5RE45T7XQCDBY2Y5UBN","short_pith_number":"pith:RW7UM2Z5","schema_version":"1.0","canonical_sha256":"8dbf466b3d8939d9fef010c38d63b40b751abf8e121ec242d3877d23aa8c131b","source":{"kind":"arxiv","id":"2301.11847","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of Pretrained Language Models for Long Clinical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Faraz S. Ahmad, Hanyin Wang, Ramsey M. Wehbe, Yikuan Li, Yuan Luo","submitted_at":"2023-01-27T16:50:29Z","abstract_excerpt":"Objective: Clinical knowledge enriched transformer models (e.g., ClinicalBERT) have state-of-the-art results on clinical NLP (natural language processing) tasks. One of the core limitations of these transformer models is the substantial memory consumption due to their full self-attention mechanism, which leads to the performance degradation in long clinical texts. To overcome this, we propose to leverage long-sequence transformer models (e.g., Longformer and BigBird), which extend the maximum input sequence length from 512 to 4096, to enhance the ability to model long-term dependencies in long"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.11847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T16:50:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57941b1c1aa5813b217569cf2f0a529f6c1ea5a20c3098c535e549974482a6db","abstract_canon_sha256":"5eb993b71b0ee8676fdc6bd4ccd08b944e646e92ff918334205edf4a9a08edd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:27.047472Z","signature_b64":"FDUBSJKgs4b5diG9xCf464qWegGA6qz35Y8zSwDpXNIak+XMrAdrRpqY7MTMJ7KuyZ77WLd7ZV3NX2xtV7cvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dbf466b3d8939d9fef010c38d63b40b751abf8e121ec242d3877d23aa8c131b","last_reissued_at":"2026-07-05T05:36:27.046964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:27.046964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Pretrained Language Models for Long Clinical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Faraz S. Ahmad, Hanyin Wang, Ramsey M. Wehbe, Yikuan Li, Yuan Luo","submitted_at":"2023-01-27T16:50:29Z","abstract_excerpt":"Objective: Clinical knowledge enriched transformer models (e.g., ClinicalBERT) have state-of-the-art results on clinical NLP (natural language processing) tasks. One of the core limitations of these transformer models is the substantial memory consumption due to their full self-attention mechanism, which leads to the performance degradation in long clinical texts. To overcome this, we propose to leverage long-sequence transformer models (e.g., Longformer and BigBird), which extend the maximum input sequence length from 512 to 4096, to enhance the ability to model long-term dependencies in long"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11847","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/2301.11847/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.11847","created_at":"2026-07-05T05:36:27.047025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11847v1","created_at":"2026-07-05T05:36:27.047025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11847","created_at":"2026-07-05T05:36:27.047025+00:00"},{"alias_kind":"pith_short_12","alias_value":"RW7UM2Z5RE45","created_at":"2026-07-05T05:36:27.047025+00:00"},{"alias_kind":"pith_short_16","alias_value":"RW7UM2Z5RE45T7XQ","created_at":"2026-07-05T05:36:27.047025+00:00"},{"alias_kind":"pith_short_8","alias_value":"RW7UM2Z5","created_at":"2026-07-05T05:36:27.047025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN","json":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN.json","graph_json":"https://pith.science/api/pith-number/RW7UM2Z5RE45T7XQCDBY2Y5UBN/graph.json","events_json":"https://pith.science/api/pith-number/RW7UM2Z5RE45T7XQCDBY2Y5UBN/events.json","paper":"https://pith.science/paper/RW7UM2Z5"},"agent_actions":{"view_html":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN","download_json":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN.json","view_paper":"https://pith.science/paper/RW7UM2Z5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11847&json=true","fetch_graph":"https://pith.science/api/pith-number/RW7UM2Z5RE45T7XQCDBY2Y5UBN/graph.json","fetch_events":"https://pith.science/api/pith-number/RW7UM2Z5RE45T7XQCDBY2Y5UBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN/action/storage_attestation","attest_author":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN/action/author_attestation","sign_citation":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN/action/citation_signature","submit_replication":"https://pith.science/pith/RW7UM2Z5RE45T7XQCDBY2Y5UBN/action/replication_record"}},"created_at":"2026-07-05T05:36:27.047025+00:00","updated_at":"2026-07-05T05:36:27.047025+00:00"}