{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7YBRQWW5DDITC5ZMZR53UOD4WI","short_pith_number":"pith:7YBRQWW5","schema_version":"1.0","canonical_sha256":"fe03185add18d131772ccc7bba387cb21e485a5951b3441fafadeefdba9be58e","source":{"kind":"arxiv","id":"2412.00554","version":2},"attestation_state":"computed","paper":{"title":"Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Barbara Di Eugenio, Lu Cheng, Yue Zhou","submitted_at":"2024-11-30T18:52:30Z","abstract_excerpt":"This paper studies the performance of large language models (LLMs), particularly regarding demographic fairness, in solving real-world healthcare tasks. We evaluate state-of-the-art LLMs with three prevalent learning frameworks across six diverse healthcare tasks and find significant challenges in applying LLMs to real-world healthcare tasks and persistent fairness issues across demographic groups. We also find that explicitly providing demographic information yields mixed results, while LLM's ability to infer such details raises concerns about biased health predictions. Utilizing LLMs as auto"},"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":"2412.00554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T18:52:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"566241435a87d1b5f11f64670f71f98ede24a88179f2c19a38725b1379679727","abstract_canon_sha256":"42e90ac244cd1607d6a6f157903bdcd95234370118b63ecc7a9fe8c7e8bac324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:59.127862Z","signature_b64":"09/E/FinILvwaen0oYXVN67DHlhlJVi/lJMqrJa+wYfNqxSbGAXJaBcFshgB94P8tMqVoqH7ZVJNsePgfajHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe03185add18d131772ccc7bba387cb21e485a5951b3441fafadeefdba9be58e","last_reissued_at":"2026-07-05T09:45:59.127403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:59.127403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Barbara Di Eugenio, Lu Cheng, Yue Zhou","submitted_at":"2024-11-30T18:52:30Z","abstract_excerpt":"This paper studies the performance of large language models (LLMs), particularly regarding demographic fairness, in solving real-world healthcare tasks. We evaluate state-of-the-art LLMs with three prevalent learning frameworks across six diverse healthcare tasks and find significant challenges in applying LLMs to real-world healthcare tasks and persistent fairness issues across demographic groups. We also find that explicitly providing demographic information yields mixed results, while LLM's ability to infer such details raises concerns about biased health predictions. Utilizing LLMs as auto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00554","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/2412.00554/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":"2412.00554","created_at":"2026-07-05T09:45:59.127459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00554v2","created_at":"2026-07-05T09:45:59.127459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00554","created_at":"2026-07-05T09:45:59.127459+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YBRQWW5DDIT","created_at":"2026-07-05T09:45:59.127459+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YBRQWW5DDITC5ZM","created_at":"2026-07-05T09:45:59.127459+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YBRQWW5","created_at":"2026-07-05T09:45:59.127459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":294,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI","json":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI.json","graph_json":"https://pith.science/api/pith-number/7YBRQWW5DDITC5ZMZR53UOD4WI/graph.json","events_json":"https://pith.science/api/pith-number/7YBRQWW5DDITC5ZMZR53UOD4WI/events.json","paper":"https://pith.science/paper/7YBRQWW5"},"agent_actions":{"view_html":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI","download_json":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI.json","view_paper":"https://pith.science/paper/7YBRQWW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00554&json=true","fetch_graph":"https://pith.science/api/pith-number/7YBRQWW5DDITC5ZMZR53UOD4WI/graph.json","fetch_events":"https://pith.science/api/pith-number/7YBRQWW5DDITC5ZMZR53UOD4WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI/action/storage_attestation","attest_author":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI/action/author_attestation","sign_citation":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI/action/citation_signature","submit_replication":"https://pith.science/pith/7YBRQWW5DDITC5ZMZR53UOD4WI/action/replication_record"}},"created_at":"2026-07-05T09:45:59.127459+00:00","updated_at":"2026-07-05T09:45:59.127459+00:00"}