{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OMLOM35D56QFO3CDLCDNZDWKQO","short_pith_number":"pith:OMLOM35D","canonical_record":{"source":{"id":"2404.05694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:24:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"465e44ab7b0bb9e5b4b5549d13f46878c8e49f5423abd5fad1b6fca140a99659","abstract_canon_sha256":"26dfba1c810d2f7c92da3f839fe8b0b06371b86d846dd1c33ca5f17f9f58cc92"},"schema_version":"1.0"},"canonical_sha256":"7316e66fa3efa0576c435886dc8eca83b2c0cfb9e0daa526b8214dfc9e78fef3","source":{"kind":"arxiv","id":"2404.05694","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05694","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05694v2","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05694","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"pith_short_12","alias_value":"OMLOM35D56QF","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"pith_short_16","alias_value":"OMLOM35D56QFO3CD","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"pith_short_8","alias_value":"OMLOM35D","created_at":"2026-07-05T08:16:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OMLOM35D56QFO3CDLCDNZDWKQO","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:24:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"465e44ab7b0bb9e5b4b5549d13f46878c8e49f5423abd5fad1b6fca140a99659","abstract_canon_sha256":"26dfba1c810d2f7c92da3f839fe8b0b06371b86d846dd1c33ca5f17f9f58cc92"},"schema_version":"1.0"},"canonical_sha256":"7316e66fa3efa0576c435886dc8eca83b2c0cfb9e0daa526b8214dfc9e78fef3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:48.760807Z","signature_b64":"I37JJzagnoGDxo0aITgSAK2jbq1AYWYRYB0kBg/+Dm3podBYRb3Fh8omUx4mcI7kfgnyynHmJZBI2M1XxZtAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7316e66fa3efa0576c435886dc8eca83b2c0cfb9e0daa526b8214dfc9e78fef3","last_reissued_at":"2026-07-05T08:16:48.760399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:48.760399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05694","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:16:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xMixZ0CVWxE0EIYK4k4Syy2m+y3PLaomaCnA9Ijy/XLuSlogN+w+1MmaNfJ2gXKk7gFbxq0R8oES0WvK/thqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:33.314159Z"},"content_sha256":"69bc0eb7bc1ad84d4318e9c7ab838e68db9720048fbca7b490feaf66ff29918e","schema_version":"1.0","event_id":"sha256:69bc0eb7bc1ad84d4318e9c7ab838e68db9720048fbca7b490feaf66ff29918e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OMLOM35D56QFO3CDLCDNZDWKQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmad Idrissi-Yaghir, Amin Dada, Christin Seifert, Christoph M. Friedrich, Cynthia S. Schmidt, Felix Nensa, Giulia Baldini, Henning Sch\\\"afer, Jan Trienes, Jeanette Bewersdorff, Jens Kleesiek, Jiang Bian, J\\\"org Schl\\\"otterer, Kaleb E. Smith, Kamyar Arzideh, Marie Bauer, Max Hasin, Peter A. Horn, Torsten Zesch, Yonghui Wu","submitted_at":"2024-04-08T17:24:04Z","abstract_excerpt":"Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can struggle in specialized domains such as medicine, where unique domain-specific terminologies, domain-specific abbreviations, and varying document structures are common. This paper explores strategies for adapting these models to domain-specific requirements, primarily through continuous pre-training on domain-specific data. We pre-trained several German medical la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05694","kind":"arxiv","version":2},"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/2404.05694/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":"2026-07-05T08:16:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYJJa6mqUZLCX7h5oWPaNwotk5LKR4JMTiOiM8qbU7Cit0c6DNr5xFafAwkGgRIMXgaJYAIfydvlbJmcROFpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:33.314558Z"},"content_sha256":"a07f973920822b5cc022b1ec508a80a687efda3bb88f5640203b736131844513","schema_version":"1.0","event_id":"sha256:a07f973920822b5cc022b1ec508a80a687efda3bb88f5640203b736131844513"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMLOM35D56QFO3CDLCDNZDWKQO/bundle.json","state_url":"https://pith.science/pith/OMLOM35D56QFO3CDLCDNZDWKQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMLOM35D56QFO3CDLCDNZDWKQO/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":"2026-07-07T08:36:33Z","links":{"resolver":"https://pith.science/pith/OMLOM35D56QFO3CDLCDNZDWKQO","bundle":"https://pith.science/pith/OMLOM35D56QFO3CDLCDNZDWKQO/bundle.json","state":"https://pith.science/pith/OMLOM35D56QFO3CDLCDNZDWKQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMLOM35D56QFO3CDLCDNZDWKQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OMLOM35D56QFO3CDLCDNZDWKQO","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":"26dfba1c810d2f7c92da3f839fe8b0b06371b86d846dd1c33ca5f17f9f58cc92","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:24:04Z","title_canon_sha256":"465e44ab7b0bb9e5b4b5549d13f46878c8e49f5423abd5fad1b6fca140a99659"},"schema_version":"1.0","source":{"id":"2404.05694","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05694","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05694v2","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05694","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"pith_short_12","alias_value":"OMLOM35D56QF","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"pith_short_16","alias_value":"OMLOM35D56QFO3CD","created_at":"2026-07-05T08:16:48Z"},{"alias_kind":"pith_short_8","alias_value":"OMLOM35D","created_at":"2026-07-05T08:16:48Z"}],"graph_snapshots":[{"event_id":"sha256:a07f973920822b5cc022b1ec508a80a687efda3bb88f5640203b736131844513","target":"graph","created_at":"2026-07-05T08:16:48Z","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/2404.05694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can struggle in specialized domains such as medicine, where unique domain-specific terminologies, domain-specific abbreviations, and varying document structures are common. This paper explores strategies for adapting these models to domain-specific requirements, primarily through continuous pre-training on domain-specific data. We pre-trained several German medical la","authors_text":"Ahmad Idrissi-Yaghir, Amin Dada, Christin Seifert, Christoph M. Friedrich, Cynthia S. Schmidt, Felix Nensa, Giulia Baldini, Henning Sch\\\"afer, Jan Trienes, Jeanette Bewersdorff, Jens Kleesiek, Jiang Bian, J\\\"org Schl\\\"otterer, Kaleb E. Smith, Kamyar Arzideh, Marie Bauer, Max Hasin, Peter A. Horn, Torsten Zesch, Yonghui Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:24:04Z","title":"Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05694","kind":"arxiv","version":2},"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":"sha256:69bc0eb7bc1ad84d4318e9c7ab838e68db9720048fbca7b490feaf66ff29918e","target":"record","created_at":"2026-07-05T08:16:48Z","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":"26dfba1c810d2f7c92da3f839fe8b0b06371b86d846dd1c33ca5f17f9f58cc92","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:24:04Z","title_canon_sha256":"465e44ab7b0bb9e5b4b5549d13f46878c8e49f5423abd5fad1b6fca140a99659"},"schema_version":"1.0","source":{"id":"2404.05694","kind":"arxiv","version":2}},"canonical_sha256":"7316e66fa3efa0576c435886dc8eca83b2c0cfb9e0daa526b8214dfc9e78fef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7316e66fa3efa0576c435886dc8eca83b2c0cfb9e0daa526b8214dfc9e78fef3","first_computed_at":"2026-07-05T08:16:48.760399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:48.760399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I37JJzagnoGDxo0aITgSAK2jbq1AYWYRYB0kBg/+Dm3podBYRb3Fh8omUx4mcI7kfgnyynHmJZBI2M1XxZtAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:48.760807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05694","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69bc0eb7bc1ad84d4318e9c7ab838e68db9720048fbca7b490feaf66ff29918e","sha256:a07f973920822b5cc022b1ec508a80a687efda3bb88f5640203b736131844513"],"state_sha256":"14cd9d13fd306e38bfaa6a729c7593dd75c95dda531262b080930e32dea0bd60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49GruA05d03Tb7Y76Ah8NOGV9F67+C1T3AWzBjaK32mSVvUFzNW6wrgkfg+3e30oHoUhbgJ3zf++lvD6D8K6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:36:33.316537Z","bundle_sha256":"2767ebc97f888733664a7b5f20c7728e3f7f1471087e1df68a824aae6131af03"}}