{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EFKQKTCA5MZBGYM43RSSBXOHN7","short_pith_number":"pith:EFKQKTCA","schema_version":"1.0","canonical_sha256":"2155054c40eb3213619cdc6520ddc76ff1b24062c2b8369e71ebe8acbc93baa6","source":{"kind":"arxiv","id":"2402.01717","version":1},"attestation_state":"computed","paper":{"title":"From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jaewoong Kim (Sungkyunkwan University), Moohong Min (Sungkyunkwan University)","submitted_at":"2024-01-26T08:23:29Z","abstract_excerpt":"Regulatory compliance in the pharmaceutical industry entails navigating through complex and voluminous guidelines, often requiring significant human resources. To address these challenges, our study introduces a chatbot model that utilizes generative AI and the Retrieval Augmented Generation (RAG) method. This chatbot is designed to search for guideline documents relevant to the user inquiries and provide answers based on the retrieved guidelines. Recognizing the inherent need for high reliability in this domain, we propose the Question and Answer Retrieval Augmented Generation (QA-RAG) model."},"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":"2402.01717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T08:23:29Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"2ddf62e9b135511778e1354e58e4be6bed9f01c437821a9efaa1f45b630e49c3","abstract_canon_sha256":"370dff18559cbc9b0255fc8d4bc41700f6063b5515312c0c443fd933a0c92211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:47.890784Z","signature_b64":"JijcYdSdUTJr1BtkaV8GlORRThUwpEMRfMtHxxJlVQNDwknu3IBBNqW3gdsMG439Bt0jtwRyB2QiERXsCGESAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2155054c40eb3213619cdc6520ddc76ff1b24062c2b8369e71ebe8acbc93baa6","last_reissued_at":"2026-07-05T07:41:47.890366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:47.890366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jaewoong Kim (Sungkyunkwan University), Moohong Min (Sungkyunkwan University)","submitted_at":"2024-01-26T08:23:29Z","abstract_excerpt":"Regulatory compliance in the pharmaceutical industry entails navigating through complex and voluminous guidelines, often requiring significant human resources. To address these challenges, our study introduces a chatbot model that utilizes generative AI and the Retrieval Augmented Generation (RAG) method. This chatbot is designed to search for guideline documents relevant to the user inquiries and provide answers based on the retrieved guidelines. Recognizing the inherent need for high reliability in this domain, we propose the Question and Answer Retrieval Augmented Generation (QA-RAG) model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01717","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/2402.01717/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":"2402.01717","created_at":"2026-07-05T07:41:47.890417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01717v1","created_at":"2026-07-05T07:41:47.890417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01717","created_at":"2026-07-05T07:41:47.890417+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFKQKTCA5MZB","created_at":"2026-07-05T07:41:47.890417+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFKQKTCA5MZBGYM4","created_at":"2026-07-05T07:41:47.890417+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFKQKTCA","created_at":"2026-07-05T07:41:47.890417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.19360","citing_title":"Compliance Management for Federated Data Processing","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7","json":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7.json","graph_json":"https://pith.science/api/pith-number/EFKQKTCA5MZBGYM43RSSBXOHN7/graph.json","events_json":"https://pith.science/api/pith-number/EFKQKTCA5MZBGYM43RSSBXOHN7/events.json","paper":"https://pith.science/paper/EFKQKTCA"},"agent_actions":{"view_html":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7","download_json":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7.json","view_paper":"https://pith.science/paper/EFKQKTCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01717&json=true","fetch_graph":"https://pith.science/api/pith-number/EFKQKTCA5MZBGYM43RSSBXOHN7/graph.json","fetch_events":"https://pith.science/api/pith-number/EFKQKTCA5MZBGYM43RSSBXOHN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7/action/storage_attestation","attest_author":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7/action/author_attestation","sign_citation":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7/action/citation_signature","submit_replication":"https://pith.science/pith/EFKQKTCA5MZBGYM43RSSBXOHN7/action/replication_record"}},"created_at":"2026-07-05T07:41:47.890417+00:00","updated_at":"2026-07-05T07:41:47.890417+00:00"}