{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LB5BVT4KNDBGR4IZEYHIXASPVD","short_pith_number":"pith:LB5BVT4K","schema_version":"1.0","canonical_sha256":"587a1acf8a68c268f119260e8b824fa8f571729be4318d93b1f909dddfed6229","source":{"kind":"arxiv","id":"2506.10896","version":1},"attestation_state":"computed","paper":{"title":"BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alistair E. W. Johnson, Antoine Chaffin, Brigitte Durieux, Charlotta Lindvall, Eric Lehman, Joshua Davis, Matthew McDermott, Thomas Sounack, Tom J. Pollard, Tristan Naumann","submitted_at":"2025-06-12T17:01:11Z","abstract_excerpt":"Encoder-based transformer models are central to biomedical and clinical Natural Language Processing (NLP), as their bidirectional self-attention makes them well-suited for efficiently extracting structured information from unstructured text through discriminative tasks. However, encoders have seen slower development compared to decoder models, leading to limited domain adaptation in biomedical and clinical settings. We introduce BioClinical ModernBERT, a domain-adapted encoder that builds on the recent ModernBERT release, incorporating long-context processing and substantial improvements in sp"},"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":"2506.10896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T17:01:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad8705f014e851361224c2b9e2bb2a99edd6716af34650c9f80c352047fc03a5","abstract_canon_sha256":"b6ef43d1a516f3a31c27da5087fe1a0aab2453647c5182ed389386042bad786b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:39.646975Z","signature_b64":"NmlzyIh+VSqQtbBu2lpTPVgcaDD1dbBRnqvYJhdIJCT7qdALxrlw7pwcNy1nWbAulNg+JR2oGkbtC8Mlts0lDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587a1acf8a68c268f119260e8b824fa8f571729be4318d93b1f909dddfed6229","last_reissued_at":"2026-07-05T11:20:39.646288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:39.646288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alistair E. W. Johnson, Antoine Chaffin, Brigitte Durieux, Charlotta Lindvall, Eric Lehman, Joshua Davis, Matthew McDermott, Thomas Sounack, Tom J. Pollard, Tristan Naumann","submitted_at":"2025-06-12T17:01:11Z","abstract_excerpt":"Encoder-based transformer models are central to biomedical and clinical Natural Language Processing (NLP), as their bidirectional self-attention makes them well-suited for efficiently extracting structured information from unstructured text through discriminative tasks. However, encoders have seen slower development compared to decoder models, leading to limited domain adaptation in biomedical and clinical settings. We introduce BioClinical ModernBERT, a domain-adapted encoder that builds on the recent ModernBERT release, incorporating long-context processing and substantial improvements in sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10896","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/2506.10896/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":"2506.10896","created_at":"2026-07-05T11:20:39.646353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10896v1","created_at":"2026-07-05T11:20:39.646353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10896","created_at":"2026-07-05T11:20:39.646353+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB5BVT4KNDBG","created_at":"2026-07-05T11:20:39.646353+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB5BVT4KNDBGR4IZ","created_at":"2026-07-05T11:20:39.646353+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB5BVT4K","created_at":"2026-07-05T11:20:39.646353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22077","citing_title":"Morphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03301","citing_title":"SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29605","citing_title":"How much of an LLM-generated clinical corpus is actually new? A production-scale measurement of content redundancy for provenance classification","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20292","citing_title":"TreeText-CTS: Compact, Source-Traceable Tree-Path Evidence for Irregular Clinical Time-Series Prediction","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12438","citing_title":"A Causal Language Modeling Detour Improves Encoder Continued Pretraining","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08482","citing_title":"ShifaMind: A Multiplicative Concept Bottleneck for Interpretable ICD-10 Coding","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03301","citing_title":"SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14547","citing_title":"Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD","json":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD.json","graph_json":"https://pith.science/api/pith-number/LB5BVT4KNDBGR4IZEYHIXASPVD/graph.json","events_json":"https://pith.science/api/pith-number/LB5BVT4KNDBGR4IZEYHIXASPVD/events.json","paper":"https://pith.science/paper/LB5BVT4K"},"agent_actions":{"view_html":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD","download_json":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD.json","view_paper":"https://pith.science/paper/LB5BVT4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10896&json=true","fetch_graph":"https://pith.science/api/pith-number/LB5BVT4KNDBGR4IZEYHIXASPVD/graph.json","fetch_events":"https://pith.science/api/pith-number/LB5BVT4KNDBGR4IZEYHIXASPVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD/action/storage_attestation","attest_author":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD/action/author_attestation","sign_citation":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD/action/citation_signature","submit_replication":"https://pith.science/pith/LB5BVT4KNDBGR4IZEYHIXASPVD/action/replication_record"}},"created_at":"2026-07-05T11:20:39.646353+00:00","updated_at":"2026-07-05T11:20:39.646353+00:00"}