{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZEGIIA33PU4DWQEQ5GLYELDGB","short_pith_number":"pith:VZEGIIA3","schema_version":"1.0","canonical_sha256":"ae4864201bdbe9c1da04874cbc1163306729addd7ea3c9686c3f140b2fa34e42","source":{"kind":"arxiv","id":"2505.23034","version":1},"attestation_state":"computed","paper":{"title":"Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guangyi Liu, Quanming Yao, Xunyuan Liu, Yongqi Zhang","submitted_at":"2025-05-29T03:20:53Z","abstract_excerpt":"Drug-drug interaction (DDI) prediction is critical for treatment safety. While large language models (LLMs) show promise in pharmaceutical tasks, their effectiveness in DDI prediction remains challenging. Inspired by the well-established clinical practice where physicians routinely reference similar historical cases to guide their decisions through case-based reasoning (CBR), we propose CBR-DDI, a novel framework that distills pharmacological principles from historical cases to improve LLM reasoning for DDI tasks. CBR-DDI constructs a knowledge repository by leveraging LLMs to extract pharmaco"},"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":"2505.23034","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T03:20:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53d213a05c9a7a1510970a48d22cb8ac657b9aafd209daaa40ad61b84db5eb1a","abstract_canon_sha256":"0b432083cd3b036b018d1d7353aac7f476dcf2691b61d875a11d53abb0a3f34e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.981877Z","signature_b64":"vzTO0H9FrDixMhwLAYRO+nhEMst34xhJO6IWlZCWhI8204kdAYmbhKw3G/TP56LoprN0ZVD9+5b7PsmLwokhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4864201bdbe9c1da04874cbc1163306729addd7ea3c9686c3f140b2fa34e42","last_reissued_at":"2026-07-05T11:11:53.981390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.981390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guangyi Liu, Quanming Yao, Xunyuan Liu, Yongqi Zhang","submitted_at":"2025-05-29T03:20:53Z","abstract_excerpt":"Drug-drug interaction (DDI) prediction is critical for treatment safety. While large language models (LLMs) show promise in pharmaceutical tasks, their effectiveness in DDI prediction remains challenging. Inspired by the well-established clinical practice where physicians routinely reference similar historical cases to guide their decisions through case-based reasoning (CBR), we propose CBR-DDI, a novel framework that distills pharmacological principles from historical cases to improve LLM reasoning for DDI tasks. CBR-DDI constructs a knowledge repository by leveraging LLMs to extract pharmaco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23034","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/2505.23034/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":"2505.23034","created_at":"2026-07-05T11:11:53.981448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23034v1","created_at":"2026-07-05T11:11:53.981448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23034","created_at":"2026-07-05T11:11:53.981448+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZEGIIA33PU4","created_at":"2026-07-05T11:11:53.981448+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZEGIIA33PU4DWQE","created_at":"2026-07-05T11:11:53.981448+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZEGIIA3","created_at":"2026-07-05T11:11:53.981448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12578","citing_title":"MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31085","citing_title":"DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06702","citing_title":"CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB","json":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB.json","graph_json":"https://pith.science/api/pith-number/VZEGIIA33PU4DWQEQ5GLYELDGB/graph.json","events_json":"https://pith.science/api/pith-number/VZEGIIA33PU4DWQEQ5GLYELDGB/events.json","paper":"https://pith.science/paper/VZEGIIA3"},"agent_actions":{"view_html":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB","download_json":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB.json","view_paper":"https://pith.science/paper/VZEGIIA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23034&json=true","fetch_graph":"https://pith.science/api/pith-number/VZEGIIA33PU4DWQEQ5GLYELDGB/graph.json","fetch_events":"https://pith.science/api/pith-number/VZEGIIA33PU4DWQEQ5GLYELDGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB/action/storage_attestation","attest_author":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB/action/author_attestation","sign_citation":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB/action/citation_signature","submit_replication":"https://pith.science/pith/VZEGIIA33PU4DWQEQ5GLYELDGB/action/replication_record"}},"created_at":"2026-07-05T11:11:53.981448+00:00","updated_at":"2026-07-05T11:11:53.981448+00:00"}