{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R6AIDFBP4PKLFMJNGZCEF7RDL7","short_pith_number":"pith:R6AIDFBP","schema_version":"1.0","canonical_sha256":"8f8081942fe3d4b2b12d364442fe235ffa6ef3f3de5f7b3418a240656688bd43","source":{"kind":"arxiv","id":"2407.05015","version":1},"attestation_state":"computed","paper":{"title":"How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adela Ljaji\\'c, Bojana Ba\\v{s}aragin, Darija Medvecki, Lorenzo Cassano, Milo\\v{s} Ko\\v{s}prdi\\'c, Nikola Milo\\v{s}evi\\'c","submitted_at":"2024-07-06T09:10:05Z","abstract_excerpt":"Large language models (LLMs) have recently become the leading source of answers for users' questions online. Despite their ability to offer eloquent answers, their accuracy and reliability can pose a significant challenge. This is especially true for sensitive domains such as biomedicine, where there is a higher need for factually correct answers. This paper introduces a biomedical retrieval-augmented generation (RAG) system designed to enhance the reliability of generated responses. The system is based on a fine-tuned LLM for the referenced question-answering, where retrieved relevant abstrac"},"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":"2407.05015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-06T09:10:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c80487aea6ab599d2cf3cfbb965bcef58a82ab4fef7191e25e613deb6a23bfb","abstract_canon_sha256":"64ff3fbb8a667738619dda335385dcf1d59ba7d872571d9f924540ed1ef0866e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:06.713780Z","signature_b64":"LbHzU0nr26itVzUQ6l9yyT8X5/2dUH8e3BHH2ukjaNYq4GYWer9KPx9L4yrqkDpujRxm2GlDppNBYa9abR1UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8081942fe3d4b2b12d364442fe235ffa6ef3f3de5f7b3418a240656688bd43","last_reissued_at":"2026-07-05T08:41:06.713325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:06.713325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adela Ljaji\\'c, Bojana Ba\\v{s}aragin, Darija Medvecki, Lorenzo Cassano, Milo\\v{s} Ko\\v{s}prdi\\'c, Nikola Milo\\v{s}evi\\'c","submitted_at":"2024-07-06T09:10:05Z","abstract_excerpt":"Large language models (LLMs) have recently become the leading source of answers for users' questions online. Despite their ability to offer eloquent answers, their accuracy and reliability can pose a significant challenge. This is especially true for sensitive domains such as biomedicine, where there is a higher need for factually correct answers. This paper introduces a biomedical retrieval-augmented generation (RAG) system designed to enhance the reliability of generated responses. The system is based on a fine-tuned LLM for the referenced question-answering, where retrieved relevant abstrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05015","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/2407.05015/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":"2407.05015","created_at":"2026-07-05T08:41:06.713390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05015v1","created_at":"2026-07-05T08:41:06.713390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05015","created_at":"2026-07-05T08:41:06.713390+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6AIDFBP4PKL","created_at":"2026-07-05T08:41:06.713390+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6AIDFBP4PKLFMJN","created_at":"2026-07-05T08:41:06.713390+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6AIDFBP","created_at":"2026-07-05T08:41:06.713390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20416","citing_title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7","json":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7.json","graph_json":"https://pith.science/api/pith-number/R6AIDFBP4PKLFMJNGZCEF7RDL7/graph.json","events_json":"https://pith.science/api/pith-number/R6AIDFBP4PKLFMJNGZCEF7RDL7/events.json","paper":"https://pith.science/paper/R6AIDFBP"},"agent_actions":{"view_html":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7","download_json":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7.json","view_paper":"https://pith.science/paper/R6AIDFBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05015&json=true","fetch_graph":"https://pith.science/api/pith-number/R6AIDFBP4PKLFMJNGZCEF7RDL7/graph.json","fetch_events":"https://pith.science/api/pith-number/R6AIDFBP4PKLFMJNGZCEF7RDL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7/action/storage_attestation","attest_author":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7/action/author_attestation","sign_citation":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7/action/citation_signature","submit_replication":"https://pith.science/pith/R6AIDFBP4PKLFMJNGZCEF7RDL7/action/replication_record"}},"created_at":"2026-07-05T08:41:06.713390+00:00","updated_at":"2026-07-05T08:41:06.713390+00:00"}