{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B2AKM5VGLU7ZPBBSDWX34TTKJ2","short_pith_number":"pith:B2AKM5VG","schema_version":"1.0","canonical_sha256":"0e80a676a65d3f9784321dafbe4e6a4eb6f8bbdf92f9b54478b7ed93948304c8","source":{"kind":"arxiv","id":"2105.02711","version":2},"attestation_state":"computed","paper":{"title":"SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cao Xiao, Chaoqi Yang, Fenglong Ma, Jimeng Sun, Lucas Glass","submitted_at":"2021-05-05T00:20:48Z","abstract_excerpt":"Medication recommendation is an essential task of AI for healthcare. Existing works focused on recommending drug combinations for patients with complex health conditions solely based on their electronic health records. Thus, they have the following limitations: (1) some important data such as drug molecule structures have not been utilized in the recommendation process. (2) drug-drug interactions (DDI) are modeled implicitly, which can lead to sub-optimal results. To address these limitations, we propose a DDI-controllable drug recommendation model named SafeDrug to leverage drugs' molecule st"},"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":"2105.02711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-05T00:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"079c5fe7cdac38eb145eaba3da36dc5fbb9e535c36e88ab7b998c549b829e7a3","abstract_canon_sha256":"3245769285094c917fae3b9d30b08bfc1e57652ea8edc1fddd3bb415b1f67375"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:23.815379Z","signature_b64":"jV35EZfJycMdODRxHZAMSAKsJzK3yOFQc4ujNNBbi+o0sQwM2ZwyXlVegQc5yIgkQvtFd58splwUN8IUTkyIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e80a676a65d3f9784321dafbe4e6a4eb6f8bbdf92f9b54478b7ed93948304c8","last_reissued_at":"2026-07-05T04:41:23.814920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:23.814920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cao Xiao, Chaoqi Yang, Fenglong Ma, Jimeng Sun, Lucas Glass","submitted_at":"2021-05-05T00:20:48Z","abstract_excerpt":"Medication recommendation is an essential task of AI for healthcare. Existing works focused on recommending drug combinations for patients with complex health conditions solely based on their electronic health records. Thus, they have the following limitations: (1) some important data such as drug molecule structures have not been utilized in the recommendation process. (2) drug-drug interactions (DDI) are modeled implicitly, which can lead to sub-optimal results. To address these limitations, we propose a DDI-controllable drug recommendation model named SafeDrug to leverage drugs' molecule st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02711","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/2105.02711/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":"2105.02711","created_at":"2026-07-05T04:41:23.814981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.02711v2","created_at":"2026-07-05T04:41:23.814981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02711","created_at":"2026-07-05T04:41:23.814981+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2AKM5VGLU7Z","created_at":"2026-07-05T04:41:23.814981+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2AKM5VGLU7ZPBBS","created_at":"2026-07-05T04:41:23.814981+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2AKM5VG","created_at":"2026-07-05T04:41:23.814981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14543","citing_title":"RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17725","citing_title":"RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2","json":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2.json","graph_json":"https://pith.science/api/pith-number/B2AKM5VGLU7ZPBBSDWX34TTKJ2/graph.json","events_json":"https://pith.science/api/pith-number/B2AKM5VGLU7ZPBBSDWX34TTKJ2/events.json","paper":"https://pith.science/paper/B2AKM5VG"},"agent_actions":{"view_html":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2","download_json":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2.json","view_paper":"https://pith.science/paper/B2AKM5VG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/B2AKM5VGLU7ZPBBSDWX34TTKJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/B2AKM5VGLU7ZPBBSDWX34TTKJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2/action/storage_attestation","attest_author":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2/action/author_attestation","sign_citation":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2/action/citation_signature","submit_replication":"https://pith.science/pith/B2AKM5VGLU7ZPBBSDWX34TTKJ2/action/replication_record"}},"created_at":"2026-07-05T04:41:23.814981+00:00","updated_at":"2026-07-05T04:41:23.814981+00:00"}