{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7K6CYVMDF2BE2G2C3Y33LE3MYP","short_pith_number":"pith:7K6CYVMD","schema_version":"1.0","canonical_sha256":"fabc2c55832e824d1b42de37b5936cc3edf1167891cd9f3182ab222807c775c9","source":{"kind":"arxiv","id":"2605.23465","version":1},"attestation_state":"computed","paper":{"title":"Iy\\`aw\\'oBench: A Benchmark for Evaluating Large Language Model Clinical Triage Accuracy on Undifferentiated Febrile Illness in Nigerian Primary Health Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Anthonio Oladimeji Gabriel, Dimeji Abdulsobur Olawuyi, Oloruntoba Ajayi, Temiloluwa Aderemi","submitted_at":"2026-05-22T10:25:51Z","abstract_excerpt":"Background. Undifferentiated febrile illness is the leading cause of primary care outpatient visits in Nigeria, yet no validated benchmark exists for evaluating large language model (LLM) clinical triage reasoning in West African primary health settings. Methods. We introduce Iy\\`aw\\'oBench v1.0, a dataset of 200 synthetic clinical vignettes across eight febrile illness categories derived from statistical distributions of 1,200 real patient encounters at 19 primary health centres (PHCs) in Oyo State, Nigeria. Six LLMs were evaluated on structured triage classification across two metrics: triag"},"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":"2605.23465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2026-05-22T10:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"d62b15c1c6cd140fd9ac2e063e7815f813d201312df53546ebb3355021be0c19","abstract_canon_sha256":"8c0e97bfa8c90121e27cb816d0d6455ca0e68a586141157ac113d524c3efdcf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:56.242801Z","signature_b64":"iUHqmUtwsG9afJCNKB6IHckD19KEb3NJDVX2OI6l8PsDmngu1DdJtLsJyDdKP9AxKKc27hSwClmIHTo5rjrlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fabc2c55832e824d1b42de37b5936cc3edf1167891cd9f3182ab222807c775c9","last_reissued_at":"2026-05-25T02:01:56.242073Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:56.242073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iy\\`aw\\'oBench: A Benchmark for Evaluating Large Language Model Clinical Triage Accuracy on Undifferentiated Febrile Illness in Nigerian Primary Health Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Anthonio Oladimeji Gabriel, Dimeji Abdulsobur Olawuyi, Oloruntoba Ajayi, Temiloluwa Aderemi","submitted_at":"2026-05-22T10:25:51Z","abstract_excerpt":"Background. Undifferentiated febrile illness is the leading cause of primary care outpatient visits in Nigeria, yet no validated benchmark exists for evaluating large language model (LLM) clinical triage reasoning in West African primary health settings. Methods. We introduce Iy\\`aw\\'oBench v1.0, a dataset of 200 synthetic clinical vignettes across eight febrile illness categories derived from statistical distributions of 1,200 real patient encounters at 19 primary health centres (PHCs) in Oyo State, Nigeria. Six LLMs were evaluated on structured triage classification across two metrics: triag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23465","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/2605.23465/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":"2605.23465","created_at":"2026-05-25T02:01:56.242186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23465v1","created_at":"2026-05-25T02:01:56.242186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23465","created_at":"2026-05-25T02:01:56.242186+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K6CYVMDF2BE","created_at":"2026-05-25T02:01:56.242186+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K6CYVMDF2BE2G2C","created_at":"2026-05-25T02:01:56.242186+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K6CYVMD","created_at":"2026-05-25T02:01:56.242186+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/7K6CYVMDF2BE2G2C3Y33LE3MYP","json":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP.json","graph_json":"https://pith.science/api/pith-number/7K6CYVMDF2BE2G2C3Y33LE3MYP/graph.json","events_json":"https://pith.science/api/pith-number/7K6CYVMDF2BE2G2C3Y33LE3MYP/events.json","paper":"https://pith.science/paper/7K6CYVMD"},"agent_actions":{"view_html":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP","download_json":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP.json","view_paper":"https://pith.science/paper/7K6CYVMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23465&json=true","fetch_graph":"https://pith.science/api/pith-number/7K6CYVMDF2BE2G2C3Y33LE3MYP/graph.json","fetch_events":"https://pith.science/api/pith-number/7K6CYVMDF2BE2G2C3Y33LE3MYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP/action/storage_attestation","attest_author":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP/action/author_attestation","sign_citation":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP/action/citation_signature","submit_replication":"https://pith.science/pith/7K6CYVMDF2BE2G2C3Y33LE3MYP/action/replication_record"}},"created_at":"2026-05-25T02:01:56.242186+00:00","updated_at":"2026-05-25T02:01:56.242186+00:00"}