{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q2ZNBYXZLG3HMWKSOMWLCSUPBP","short_pith_number":"pith:Q2ZNBYXZ","schema_version":"1.0","canonical_sha256":"86b2d0e2f959b6765952732cb14a8f0bdedf9bc587d19195007cebd58c330e1b","source":{"kind":"arxiv","id":"2607.06641","version":1},"attestation_state":"computed","paper":{"title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bethany Pace-Bonello, Fan Grayson, Felix Feldman, Joshua Harris, Leo Loman, Michael Borowitz, Ollie Higgins, Poonam Soma, Timothy Laurence, Toby Nonnenmacher","submitted_at":"2026-07-07T14:47:42Z","abstract_excerpt":"Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance. Retrieval-Augmented Generation (RAG) mitigates these risks by grounding responses in an explicitly maintained corpus, but end-to-end performance depends critically on retrieval configuration and on evaluation beyond multiple-choice formats. We extend PubHealthBench, a question answering (QA) benchmark of 7,929 questions derived from UK Government public health guidance, into a retrieval-aug"},"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":"2607.06641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T14:47:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"198c630ec9356e02cc483a77c6e442ecb63edfc50eebc41e516b9810be0438df","abstract_canon_sha256":"6d61f993d7c1dea4e193bab828d3ab5f7eb8571d4cf7f69af287a61096c6a437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:21.466190Z","signature_b64":"b/zU8+rmRbfv2Vvmw/VEpXm8ZsV8G7Lk3axoLjFp/NkkJ1qpjaF7ArEszgS5Yktqt75K+PYAvL8hmjRn+MY6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b2d0e2f959b6765952732cb14a8f0bdedf9bc587d19195007cebd58c330e1b","last_reissued_at":"2026-07-09T00:19:21.465682Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:21.465682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bethany Pace-Bonello, Fan Grayson, Felix Feldman, Joshua Harris, Leo Loman, Michael Borowitz, Ollie Higgins, Poonam Soma, Timothy Laurence, Toby Nonnenmacher","submitted_at":"2026-07-07T14:47:42Z","abstract_excerpt":"Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance. Retrieval-Augmented Generation (RAG) mitigates these risks by grounding responses in an explicitly maintained corpus, but end-to-end performance depends critically on retrieval configuration and on evaluation beyond multiple-choice formats. We extend PubHealthBench, a question answering (QA) benchmark of 7,929 questions derived from UK Government public health guidance, into a retrieval-aug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06641","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/2607.06641/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":"2607.06641","created_at":"2026-07-09T00:19:21.465760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06641v1","created_at":"2026-07-09T00:19:21.465760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06641","created_at":"2026-07-09T00:19:21.465760+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2ZNBYXZLG3H","created_at":"2026-07-09T00:19:21.465760+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2ZNBYXZLG3HMWKS","created_at":"2026-07-09T00:19:21.465760+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2ZNBYXZ","created_at":"2026-07-09T00:19:21.465760+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/Q2ZNBYXZLG3HMWKSOMWLCSUPBP","json":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP.json","graph_json":"https://pith.science/api/pith-number/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/graph.json","events_json":"https://pith.science/api/pith-number/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/events.json","paper":"https://pith.science/paper/Q2ZNBYXZ"},"agent_actions":{"view_html":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP","download_json":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP.json","view_paper":"https://pith.science/paper/Q2ZNBYXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06641&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/action/storage_attestation","attest_author":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/action/author_attestation","sign_citation":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/action/citation_signature","submit_replication":"https://pith.science/pith/Q2ZNBYXZLG3HMWKSOMWLCSUPBP/action/replication_record"}},"created_at":"2026-07-09T00:19:21.465760+00:00","updated_at":"2026-07-09T00:19:21.465760+00:00"}