{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JOPBWJA6YDFOJ7HISWYEYNDBWY","short_pith_number":"pith:JOPBWJA6","schema_version":"1.0","canonical_sha256":"4b9e1b241ec0cae4fce895b04c3461b608655a1ed94ca8fbfdecb46475c78726","source":{"kind":"arxiv","id":"2403.14578","version":1},"attestation_state":"computed","paper":{"title":"RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Edward R. Morrell, Gabriela van Bergen Gonzalez Bueno, Lea Goetz, Rafael Poyiadzi, William James Bolton","submitted_at":"2024-03-21T17:30:59Z","abstract_excerpt":"Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LL"},"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":"2403.14578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T17:30:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d3538a98de1028a9c457040ddd283ce51e68db4d71ac22f13d9bc6e246893748","abstract_canon_sha256":"9dae3ce2d598c90c3e1134ac86bd78febabb8a5e2db4276b4055096ce9a535d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:11.059308Z","signature_b64":"Z81OacKd85Y6C3Ehg63DCFThm+PzpdUOjGahc8c2xvzY7xzyqW9zJGzzY6LIMRGLB3QnliqZb1Kyor/7672hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9e1b241ec0cae4fce895b04c3461b608655a1ed94ca8fbfdecb46475c78726","last_reissued_at":"2026-07-05T07:59:11.058762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:11.058762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Edward R. Morrell, Gabriela van Bergen Gonzalez Bueno, Lea Goetz, Rafael Poyiadzi, William James Bolton","submitted_at":"2024-03-21T17:30:59Z","abstract_excerpt":"Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14578","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/2403.14578/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":"2403.14578","created_at":"2026-07-05T07:59:11.058825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14578v1","created_at":"2026-07-05T07:59:11.058825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14578","created_at":"2026-07-05T07:59:11.058825+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOPBWJA6YDFO","created_at":"2026-07-05T07:59:11.058825+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOPBWJA6YDFOJ7HI","created_at":"2026-07-05T07:59:11.058825+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOPBWJA6","created_at":"2026-07-05T07:59:11.058825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06913","citing_title":"Evaluating LLM Robustness Under Domain-Specific Prompt Perturbations in Public Health Applications","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07237","citing_title":"When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY","json":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY.json","graph_json":"https://pith.science/api/pith-number/JOPBWJA6YDFOJ7HISWYEYNDBWY/graph.json","events_json":"https://pith.science/api/pith-number/JOPBWJA6YDFOJ7HISWYEYNDBWY/events.json","paper":"https://pith.science/paper/JOPBWJA6"},"agent_actions":{"view_html":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY","download_json":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY.json","view_paper":"https://pith.science/paper/JOPBWJA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14578&json=true","fetch_graph":"https://pith.science/api/pith-number/JOPBWJA6YDFOJ7HISWYEYNDBWY/graph.json","fetch_events":"https://pith.science/api/pith-number/JOPBWJA6YDFOJ7HISWYEYNDBWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY/action/storage_attestation","attest_author":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY/action/author_attestation","sign_citation":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY/action/citation_signature","submit_replication":"https://pith.science/pith/JOPBWJA6YDFOJ7HISWYEYNDBWY/action/replication_record"}},"created_at":"2026-07-05T07:59:11.058825+00:00","updated_at":"2026-07-05T07:59:11.058825+00:00"}