{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RGGIZQJO6M6LNUZKIR27JYVAG5","short_pith_number":"pith:RGGIZQJO","schema_version":"1.0","canonical_sha256":"898c8cc12ef33cb6d32a4475f4e2a0377dcd83ec362c99fe11f336db1b7d6a5e","source":{"kind":"arxiv","id":"2409.20147","version":1},"attestation_state":"computed","paper":{"title":"Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Claes N. Ladefoged, Desmond Elliott, Gitte M. Knudsen, Helene Kaas, Lars H. Pinborg, Martin Prener, Melanie Ganz, Vincent Beliveau","submitted_at":"2024-09-30T09:52:28Z","abstract_excerpt":"Natural language processing (NLP) in the medical domain can underperform in real-world applications involving small datasets in a non-English language with few labeled samples and imbalanced classes. There is yet no consensus on how to approach this problem. We evaluated a set of NLP models including BERT-like transformers, few-shot learning with sentence transformers (SetFit), and prompted large language models (LLM), using three datasets of radiology reports on magnetic resonance images of epilepsy patients in Danish, a low-resource language. Our results indicate that BERT-like models pretra"},"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":"2409.20147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T09:52:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e347bf2797c8c7a69ff5c72c3e83397a8c0f38df7eb14ecbb9ac2e1d492bc2c9","abstract_canon_sha256":"7599b095bc4f3f6d58dd9f25f7a378fbb81ffde2af6d588b794cb2d9105eeb8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:39.680890Z","signature_b64":"YT/lXodOE7cJIo+Fcg5kxmPrSu1czM56gRueI7XiNgLnE4fFTuQ+zh4cqeYh7gEUNnR+fsQjIP64Z1Pl1JSTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"898c8cc12ef33cb6d32a4475f4e2a0377dcd83ec362c99fe11f336db1b7d6a5e","last_reissued_at":"2026-07-05T09:13:39.680428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:39.680428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Claes N. Ladefoged, Desmond Elliott, Gitte M. Knudsen, Helene Kaas, Lars H. Pinborg, Martin Prener, Melanie Ganz, Vincent Beliveau","submitted_at":"2024-09-30T09:52:28Z","abstract_excerpt":"Natural language processing (NLP) in the medical domain can underperform in real-world applications involving small datasets in a non-English language with few labeled samples and imbalanced classes. There is yet no consensus on how to approach this problem. We evaluated a set of NLP models including BERT-like transformers, few-shot learning with sentence transformers (SetFit), and prompted large language models (LLM), using three datasets of radiology reports on magnetic resonance images of epilepsy patients in Danish, a low-resource language. Our results indicate that BERT-like models pretra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20147","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/2409.20147/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":"2409.20147","created_at":"2026-07-05T09:13:39.680482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20147v1","created_at":"2026-07-05T09:13:39.680482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20147","created_at":"2026-07-05T09:13:39.680482+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGGIZQJO6M6L","created_at":"2026-07-05T09:13:39.680482+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGGIZQJO6M6LNUZK","created_at":"2026-07-05T09:13:39.680482+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGGIZQJO","created_at":"2026-07-05T09:13:39.680482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04471","citing_title":"MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5","json":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5.json","graph_json":"https://pith.science/api/pith-number/RGGIZQJO6M6LNUZKIR27JYVAG5/graph.json","events_json":"https://pith.science/api/pith-number/RGGIZQJO6M6LNUZKIR27JYVAG5/events.json","paper":"https://pith.science/paper/RGGIZQJO"},"agent_actions":{"view_html":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5","download_json":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5.json","view_paper":"https://pith.science/paper/RGGIZQJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20147&json=true","fetch_graph":"https://pith.science/api/pith-number/RGGIZQJO6M6LNUZKIR27JYVAG5/graph.json","fetch_events":"https://pith.science/api/pith-number/RGGIZQJO6M6LNUZKIR27JYVAG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5/action/storage_attestation","attest_author":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5/action/author_attestation","sign_citation":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5/action/citation_signature","submit_replication":"https://pith.science/pith/RGGIZQJO6M6LNUZKIR27JYVAG5/action/replication_record"}},"created_at":"2026-07-05T09:13:39.680482+00:00","updated_at":"2026-07-05T09:13:39.680482+00:00"}