{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PCM5EQGZMFF67QCGXYRYC5AEYC","short_pith_number":"pith:PCM5EQGZ","schema_version":"1.0","canonical_sha256":"7899d240d9614befc046be23817404c0b0c41137728c368bc75a678e40a09e21","source":{"kind":"arxiv","id":"2504.03964","version":1},"attestation_state":"computed","paper":{"title":"Clinical ModernBERT: An efficient and long context encoder for biomedical text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony Wu, Jeffrey N. Chiang, Simon A. Lee","submitted_at":"2025-04-04T22:14:12Z","abstract_excerpt":"We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at pro"},"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":"2504.03964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T22:14:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5d7ef273c2aa182f3de542561e1fbc5d9fad5c490222ceb4b995c0b578e740e4","abstract_canon_sha256":"0d9b6d548b921ef39d34fca4b1bccb75161f3646ddfcecc96ae7e520421a018e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:52.000044Z","signature_b64":"hBY9eOqp8TRFKiss4U7y2vzoch6pqkZNFRcaM6EPjnzAbUSRFHAEZXcOpUoK/fV2SdeV98VG0FO5DL3i0Nr3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7899d240d9614befc046be23817404c0b0c41137728c368bc75a678e40a09e21","last_reissued_at":"2026-07-05T10:44:51.999531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:51.999531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clinical ModernBERT: An efficient and long context encoder for biomedical text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony Wu, Jeffrey N. Chiang, Simon A. Lee","submitted_at":"2025-04-04T22:14:12Z","abstract_excerpt":"We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03964","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/2504.03964/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":"2504.03964","created_at":"2026-07-05T10:44:51.999602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03964v1","created_at":"2026-07-05T10:44:51.999602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03964","created_at":"2026-07-05T10:44:51.999602+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCM5EQGZMFF6","created_at":"2026-07-05T10:44:51.999602+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCM5EQGZMFF67QCG","created_at":"2026-07-05T10:44:51.999602+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCM5EQGZ","created_at":"2026-07-05T10:44:51.999602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22079","citing_title":"Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02812","citing_title":"Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12438","citing_title":"A Causal Language Modeling Detour Improves Encoder Continued Pretraining","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09765","citing_title":"WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC","json":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC.json","graph_json":"https://pith.science/api/pith-number/PCM5EQGZMFF67QCGXYRYC5AEYC/graph.json","events_json":"https://pith.science/api/pith-number/PCM5EQGZMFF67QCGXYRYC5AEYC/events.json","paper":"https://pith.science/paper/PCM5EQGZ"},"agent_actions":{"view_html":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC","download_json":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC.json","view_paper":"https://pith.science/paper/PCM5EQGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03964&json=true","fetch_graph":"https://pith.science/api/pith-number/PCM5EQGZMFF67QCGXYRYC5AEYC/graph.json","fetch_events":"https://pith.science/api/pith-number/PCM5EQGZMFF67QCGXYRYC5AEYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC/action/storage_attestation","attest_author":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC/action/author_attestation","sign_citation":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC/action/citation_signature","submit_replication":"https://pith.science/pith/PCM5EQGZMFF67QCGXYRYC5AEYC/action/replication_record"}},"created_at":"2026-07-05T10:44:51.999602+00:00","updated_at":"2026-07-05T10:44:51.999602+00:00"}