{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X6XLPECZSM22WJJ6BJ3GE4WTQ3","short_pith_number":"pith:X6XLPECZ","schema_version":"1.0","canonical_sha256":"bfaeb790599335ab253e0a766272d386dcdd70c8d4c8008f2a7d215a41c91734","source":{"kind":"arxiv","id":"2601.03471","version":3},"attestation_state":"computed","paper":{"title":"EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Dehai Min, Guanchen Wu, Lu Cheng, Max S. Y. Lau, Mingyang Wei, Qi He, Wei Jin, Yuzhang Xie, Zewen Liu, Ziyang Zhang","submitted_at":"2026-01-06T23:49:10Z","abstract_excerpt":"Reliable epidemiological reasoning requires synthesizing study evidence to infer disease burden, transmission dynamics, and intervention effects at the population level. Existing medical question answering benchmarks primarily emphasize clinical knowledge or patient-level reasoning, yet few systematically evaluate evidence-grounded epidemiological inference. We present EpiQAL, the first diagnostic benchmark for epidemiological question answering across diverse diseases, comprising three subsets built from open-access literature. The three subsets progressively test factual recall, multi-step i"},"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":"2601.03471","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T23:49:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1fac1bc2c1470886d3a161068975a42fbfffbc607bdea7f1e09a0a5f5a2b5e73","abstract_canon_sha256":"4f9fe81117f072cda98f2aedf7a513875eadb6b3b0526fdd98e5d072b156f5e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:42.138656Z","signature_b64":"LKTsv4gJiRSLtTjSj2qKfbqqY99rFAfGyIJdOOedfyGVgjZF5d1vUp5T9gaYAEVsVYdE2f761rOJIMhovXXhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfaeb790599335ab253e0a766272d386dcdd70c8d4c8008f2a7d215a41c91734","last_reissued_at":"2026-05-27T01:05:42.137991Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:42.137991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Dehai Min, Guanchen Wu, Lu Cheng, Max S. Y. Lau, Mingyang Wei, Qi He, Wei Jin, Yuzhang Xie, Zewen Liu, Ziyang Zhang","submitted_at":"2026-01-06T23:49:10Z","abstract_excerpt":"Reliable epidemiological reasoning requires synthesizing study evidence to infer disease burden, transmission dynamics, and intervention effects at the population level. Existing medical question answering benchmarks primarily emphasize clinical knowledge or patient-level reasoning, yet few systematically evaluate evidence-grounded epidemiological inference. We present EpiQAL, the first diagnostic benchmark for epidemiological question answering across diverse diseases, comprising three subsets built from open-access literature. The three subsets progressively test factual recall, multi-step i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03471","kind":"arxiv","version":3},"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/2601.03471/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":"2601.03471","created_at":"2026-05-27T01:05:42.138063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.03471v3","created_at":"2026-05-27T01:05:42.138063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03471","created_at":"2026-05-27T01:05:42.138063+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6XLPECZSM22","created_at":"2026-05-27T01:05:42.138063+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6XLPECZSM22WJJ6","created_at":"2026-05-27T01:05:42.138063+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6XLPECZ","created_at":"2026-05-27T01:05:42.138063+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/X6XLPECZSM22WJJ6BJ3GE4WTQ3","json":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3.json","graph_json":"https://pith.science/api/pith-number/X6XLPECZSM22WJJ6BJ3GE4WTQ3/graph.json","events_json":"https://pith.science/api/pith-number/X6XLPECZSM22WJJ6BJ3GE4WTQ3/events.json","paper":"https://pith.science/paper/X6XLPECZ"},"agent_actions":{"view_html":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3","download_json":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3.json","view_paper":"https://pith.science/paper/X6XLPECZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.03471&json=true","fetch_graph":"https://pith.science/api/pith-number/X6XLPECZSM22WJJ6BJ3GE4WTQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/X6XLPECZSM22WJJ6BJ3GE4WTQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3/action/storage_attestation","attest_author":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3/action/author_attestation","sign_citation":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3/action/citation_signature","submit_replication":"https://pith.science/pith/X6XLPECZSM22WJJ6BJ3GE4WTQ3/action/replication_record"}},"created_at":"2026-05-27T01:05:42.138063+00:00","updated_at":"2026-05-27T01:05:42.138063+00:00"}