{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2UV767KRV2ZAQIFKDCYLZI6MYA","short_pith_number":"pith:2UV767KR","schema_version":"1.0","canonical_sha256":"d52bff7d51aeb20820aa18b0bca3ccc0372bbfa0e956aa51c46bc259bd1351c7","source":{"kind":"arxiv","id":"2505.20218","version":2},"attestation_state":"computed","paper":{"title":"Fine-grained List-wise Alignment for Generative Medication Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenxiao Fan, Chongming Gao, Fuli Feng, Wentao Shi, Yaxin Gong, Zihao Zhao","submitted_at":"2025-05-26T16:59:23Z","abstract_excerpt":"Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise prediction paradigms that overlook synergistic drug effects and potential adverse drug-drug interactions (DDIs). We propose FLAME, a fine-grained list-wise alignment framework for large language models (LLMs), enabling drug-by-drug generation of drug lists. FLAME formulates recommendation as a sequential decision process, where each step adds or removes a single drug. To provide fine-grained learning signals, we devis"},"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":"2505.20218","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T16:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"a4b09efd81551d021debf57972a1867fc0602c8582915c3e1d3e903538a03b88","abstract_canon_sha256":"92d95528cb178fb15b337437ba9c2227893e470a59695ad6f0de70d02786d00f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:29.186700Z","signature_b64":"33l73e5k2xPme1DcGMhuJs8evryRmiKOO8++TbSJAWFeXBFxyAmhiHgqnA3y7RI5YBdQHN6kZyvKkKYXaMXwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d52bff7d51aeb20820aa18b0bca3ccc0372bbfa0e956aa51c46bc259bd1351c7","last_reissued_at":"2026-05-20T00:05:29.185701Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:29.185701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained List-wise Alignment for Generative Medication Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenxiao Fan, Chongming Gao, Fuli Feng, Wentao Shi, Yaxin Gong, Zihao Zhao","submitted_at":"2025-05-26T16:59:23Z","abstract_excerpt":"Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise prediction paradigms that overlook synergistic drug effects and potential adverse drug-drug interactions (DDIs). We propose FLAME, a fine-grained list-wise alignment framework for large language models (LLMs), enabling drug-by-drug generation of drug lists. FLAME formulates recommendation as a sequential decision process, where each step adds or removes a single drug. To provide fine-grained learning signals, we devis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20218","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/2505.20218/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":"2505.20218","created_at":"2026-05-20T00:05:29.185878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20218v2","created_at":"2026-05-20T00:05:29.185878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20218","created_at":"2026-05-20T00:05:29.185878+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UV767KRV2ZA","created_at":"2026-05-20T00:05:29.185878+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UV767KRV2ZAQIFK","created_at":"2026-05-20T00:05:29.185878+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UV767KR","created_at":"2026-05-20T00:05:29.185878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.08559","citing_title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","ref_index":130,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA","json":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA.json","graph_json":"https://pith.science/api/pith-number/2UV767KRV2ZAQIFKDCYLZI6MYA/graph.json","events_json":"https://pith.science/api/pith-number/2UV767KRV2ZAQIFKDCYLZI6MYA/events.json","paper":"https://pith.science/paper/2UV767KR"},"agent_actions":{"view_html":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA","download_json":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA.json","view_paper":"https://pith.science/paper/2UV767KR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20218&json=true","fetch_graph":"https://pith.science/api/pith-number/2UV767KRV2ZAQIFKDCYLZI6MYA/graph.json","fetch_events":"https://pith.science/api/pith-number/2UV767KRV2ZAQIFKDCYLZI6MYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA/action/storage_attestation","attest_author":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA/action/author_attestation","sign_citation":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA/action/citation_signature","submit_replication":"https://pith.science/pith/2UV767KRV2ZAQIFKDCYLZI6MYA/action/replication_record"}},"created_at":"2026-05-20T00:05:29.185878+00:00","updated_at":"2026-05-20T00:05:29.185878+00:00"}