{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUAU4ZF4M3CPGM7GL5JDK6H7M2","short_pith_number":"pith:PUAU4ZF4","schema_version":"1.0","canonical_sha256":"7d014e64bc66c4f333e65f523578ff66a24f47d0bb83bf4c50d1e33458c0d170","source":{"kind":"arxiv","id":"2407.18322","version":2},"attestation_state":"computed","paper":{"title":"The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew Bate, Andrew Beam, Chiho Sato, Darmendra Ramcharran, Greg Powell, Jeffery L Painter, Joe B Hakim, Paulina Sobczak, Vijay Kara","submitted_at":"2024-07-01T19:52:41Z","abstract_excerpt":"Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, LLM deployments in high-risk and safety-critical domains pose unique challenges, notably the issue of ``hallucination,'' where LLMs can generate fabricated information. This is particularly concerning in settings such as drug safety, where inaccuracies could lead to patient harm. To mitigate these risks, we have developed and demonstrated a proof of concept suite of guardrails specifically designed to mitigate certain types of hallucinations and errors"},"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":"2407.18322","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T19:52:41Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"d3ecff4d0be93f07b31dddceb88e900c379e5719671d23bd7859a705c8d9666c","abstract_canon_sha256":"c8d9d7501747729446d8c7000d259c87f2700d13bb2991150e4affb09d50ea80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:01.671228Z","signature_b64":"rVVCbAcGj13+vdUqDNSmNddpWicknEEcLHPtBHqQ1IC/wm4hGQhsxJpTICaskdA2ZooI64VanfI/QI4dkGsJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d014e64bc66c4f333e65f523578ff66a24f47d0bb83bf4c50d1e33458c0d170","last_reissued_at":"2026-07-05T09:03:01.670770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:01.670770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew Bate, Andrew Beam, Chiho Sato, Darmendra Ramcharran, Greg Powell, Jeffery L Painter, Joe B Hakim, Paulina Sobczak, Vijay Kara","submitted_at":"2024-07-01T19:52:41Z","abstract_excerpt":"Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, LLM deployments in high-risk and safety-critical domains pose unique challenges, notably the issue of ``hallucination,'' where LLMs can generate fabricated information. This is particularly concerning in settings such as drug safety, where inaccuracies could lead to patient harm. To mitigate these risks, we have developed and demonstrated a proof of concept suite of guardrails specifically designed to mitigate certain types of hallucinations and errors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18322","kind":"arxiv","version":2},"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/2407.18322/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":"2407.18322","created_at":"2026-07-05T09:03:01.670830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18322v2","created_at":"2026-07-05T09:03:01.670830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18322","created_at":"2026-07-05T09:03:01.670830+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUAU4ZF4M3CP","created_at":"2026-07-05T09:03:01.670830+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUAU4ZF4M3CPGM7G","created_at":"2026-07-05T09:03:01.670830+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUAU4ZF4","created_at":"2026-07-05T09:03:01.670830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28332","citing_title":"When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22373","citing_title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22373","citing_title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2","json":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2.json","graph_json":"https://pith.science/api/pith-number/PUAU4ZF4M3CPGM7GL5JDK6H7M2/graph.json","events_json":"https://pith.science/api/pith-number/PUAU4ZF4M3CPGM7GL5JDK6H7M2/events.json","paper":"https://pith.science/paper/PUAU4ZF4"},"agent_actions":{"view_html":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2","download_json":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2.json","view_paper":"https://pith.science/paper/PUAU4ZF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18322&json=true","fetch_graph":"https://pith.science/api/pith-number/PUAU4ZF4M3CPGM7GL5JDK6H7M2/graph.json","fetch_events":"https://pith.science/api/pith-number/PUAU4ZF4M3CPGM7GL5JDK6H7M2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2/action/storage_attestation","attest_author":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2/action/author_attestation","sign_citation":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2/action/citation_signature","submit_replication":"https://pith.science/pith/PUAU4ZF4M3CPGM7GL5JDK6H7M2/action/replication_record"}},"created_at":"2026-07-05T09:03:01.670830+00:00","updated_at":"2026-07-05T09:03:01.670830+00:00"}