{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EF74PE27LB4TZJXFLSDB4VULTL","short_pith_number":"pith:EF74PE27","schema_version":"1.0","canonical_sha256":"217fc7935f58793ca6e55c861e568b9aee1a00a76d84ae929a0704650128d326","source":{"kind":"arxiv","id":"2606.03250","version":1},"attestation_state":"computed","paper":{"title":"The Word and the Way: Strategies for Domain-Specific BERT Pre-Training in German Medical NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Henry He, Johann Frei, Raphael Schmitt","submitted_at":"2026-06-02T07:10:43Z","abstract_excerpt":"Digital healthcare generates vast amounts of clinical text that can support AI-assisted applications, yet German biomedical language models remain limited by older architectures or restricted training data. We present ChristBERT (Clinical- and Healthcare-Related Issues and Subjects Tuned BERT), a family of domain-specific German RoBERTa-based language models trained on a 13.5GB corpus of scientific publications, clinical texts, health-related web content, and translated clinical resources. To investigate the impact of domain adaptation strategies in German clinical NLP, we compare continued pr"},"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":"2606.03250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T07:10:43Z","cross_cats_sorted":[],"title_canon_sha256":"c14e33e7d3bd12123d72dbfffed508078aa69ca7a04c8b93bb612edd88c58f7a","abstract_canon_sha256":"3ca9c550d3e163a60b9336683bc982e778657662e494d48fed67e67b2380ff57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:36.260814Z","signature_b64":"gUlBvj6FkMC4smAnO6K6fGgvHSltuvrgfCVGIBWGoNCNcmHIml42arIYj57euqqZB2zeqMHyHuyTARZD3b63DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217fc7935f58793ca6e55c861e568b9aee1a00a76d84ae929a0704650128d326","last_reissued_at":"2026-06-03T01:05:36.260417Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:36.260417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Word and the Way: Strategies for Domain-Specific BERT Pre-Training in German Medical NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Henry He, Johann Frei, Raphael Schmitt","submitted_at":"2026-06-02T07:10:43Z","abstract_excerpt":"Digital healthcare generates vast amounts of clinical text that can support AI-assisted applications, yet German biomedical language models remain limited by older architectures or restricted training data. We present ChristBERT (Clinical- and Healthcare-Related Issues and Subjects Tuned BERT), a family of domain-specific German RoBERTa-based language models trained on a 13.5GB corpus of scientific publications, clinical texts, health-related web content, and translated clinical resources. To investigate the impact of domain adaptation strategies in German clinical NLP, we compare continued pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03250","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/2606.03250/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":"2606.03250","created_at":"2026-06-03T01:05:36.260468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03250v1","created_at":"2026-06-03T01:05:36.260468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03250","created_at":"2026-06-03T01:05:36.260468+00:00"},{"alias_kind":"pith_short_12","alias_value":"EF74PE27LB4T","created_at":"2026-06-03T01:05:36.260468+00:00"},{"alias_kind":"pith_short_16","alias_value":"EF74PE27LB4TZJXF","created_at":"2026-06-03T01:05:36.260468+00:00"},{"alias_kind":"pith_short_8","alias_value":"EF74PE27","created_at":"2026-06-03T01:05:36.260468+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/EF74PE27LB4TZJXFLSDB4VULTL","json":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL.json","graph_json":"https://pith.science/api/pith-number/EF74PE27LB4TZJXFLSDB4VULTL/graph.json","events_json":"https://pith.science/api/pith-number/EF74PE27LB4TZJXFLSDB4VULTL/events.json","paper":"https://pith.science/paper/EF74PE27"},"agent_actions":{"view_html":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL","download_json":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL.json","view_paper":"https://pith.science/paper/EF74PE27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03250&json=true","fetch_graph":"https://pith.science/api/pith-number/EF74PE27LB4TZJXFLSDB4VULTL/graph.json","fetch_events":"https://pith.science/api/pith-number/EF74PE27LB4TZJXFLSDB4VULTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL/action/storage_attestation","attest_author":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL/action/author_attestation","sign_citation":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL/action/citation_signature","submit_replication":"https://pith.science/pith/EF74PE27LB4TZJXFLSDB4VULTL/action/replication_record"}},"created_at":"2026-06-03T01:05:36.260468+00:00","updated_at":"2026-06-03T01:05:36.260468+00:00"}