{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JOPBWJA6YDFOJ7HISWYEYNDBWY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9dae3ce2d598c90c3e1134ac86bd78febabb8a5e2db4276b4055096ce9a535d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T17:30:59Z","title_canon_sha256":"d3538a98de1028a9c457040ddd283ce51e68db4d71ac22f13d9bc6e246893748"},"schema_version":"1.0","source":{"id":"2403.14578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14578","created_at":"2026-07-05T07:59:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14578v1","created_at":"2026-07-05T07:59:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14578","created_at":"2026-07-05T07:59:11Z"},{"alias_kind":"pith_short_12","alias_value":"JOPBWJA6YDFO","created_at":"2026-07-05T07:59:11Z"},{"alias_kind":"pith_short_16","alias_value":"JOPBWJA6YDFOJ7HI","created_at":"2026-07-05T07:59:11Z"},{"alias_kind":"pith_short_8","alias_value":"JOPBWJA6","created_at":"2026-07-05T07:59:11Z"}],"graph_snapshots":[{"event_id":"sha256:7e651d7c588e79f484ba6e5fda7ea55f96951b4ed5a50abbf2719f6c6dc948b8","target":"graph","created_at":"2026-07-05T07:59:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.14578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Edward R. Morrell, Gabriela van Bergen Gonzalez Bueno, Lea Goetz, Rafael Poyiadzi, William James Bolton","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T17:30:59Z","title":"RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14578","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d65c32c8b015303ce2b40f506ecef180c65ff02bcc2baef57ac885fae07abbf2","target":"record","created_at":"2026-07-05T07:59:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9dae3ce2d598c90c3e1134ac86bd78febabb8a5e2db4276b4055096ce9a535d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T17:30:59Z","title_canon_sha256":"d3538a98de1028a9c457040ddd283ce51e68db4d71ac22f13d9bc6e246893748"},"schema_version":"1.0","source":{"id":"2403.14578","kind":"arxiv","version":1}},"canonical_sha256":"4b9e1b241ec0cae4fce895b04c3461b608655a1ed94ca8fbfdecb46475c78726","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b9e1b241ec0cae4fce895b04c3461b608655a1ed94ca8fbfdecb46475c78726","first_computed_at":"2026-07-05T07:59:11.058762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:11.058762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z81OacKd85Y6C3Ehg63DCFThm+PzpdUOjGahc8c2xvzY7xzyqW9zJGzzY6LIMRGLB3QnliqZb1Kyor/7672hCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:11.059308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d65c32c8b015303ce2b40f506ecef180c65ff02bcc2baef57ac885fae07abbf2","sha256:7e651d7c588e79f484ba6e5fda7ea55f96951b4ed5a50abbf2719f6c6dc948b8"],"state_sha256":"be2eeef62fcd3d7d02054daf7984bc479c73ea633031aad0faf3acfb9bf985cb"}