{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EV5B7ZTOSLCPBA32K6MLWH7SHS","short_pith_number":"pith:EV5B7ZTO","schema_version":"1.0","canonical_sha256":"257a1fe66e92c4f0837a5798bb1ff23ca1c0dacb3b33283ba7d8f2dc88831e50","source":{"kind":"arxiv","id":"2606.31085","version":1},"attestation_state":"computed","paper":{"title":"DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Quanming Yao, Xiaoyi Fu, Yu Liu, Zhenqian Shen","submitted_at":"2026-06-30T03:19:33Z","abstract_excerpt":"Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms. We propose DDIAgents, a mechanism-conditioned multi-agent framework that performs DDI prediction through dynamic knowledge orchestration. Given a drug pair, a planner agent instantiates specialized expert agents, routes mechanism-relevant knowledge sources to each agent, and aggregates their analyses through a conclusion agent. By adapting context flow to the inferred interaction mechanism, DDIAgents r"},"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":"2606.31085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T03:19:33Z","cross_cats_sorted":[],"title_canon_sha256":"311b87f1afe2b33639254ac2c789b9a118b498cb16d40bc5b5872b7bd7914c97","abstract_canon_sha256":"a6d32ee5a3153b869f2800e71380977fe11528a5d2863c770c768156b6044388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:28.611843Z","signature_b64":"LNNft4I8aLvC6huNdkbGaxMMSLdlH1YYEi9DwTp2K9yCcifi3EiIRqmUowF6e9pgzeTqLWjKQuR9/ESnlbJ+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"257a1fe66e92c4f0837a5798bb1ff23ca1c0dacb3b33283ba7d8f2dc88831e50","last_reissued_at":"2026-07-01T01:17:28.611403Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:28.611403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Quanming Yao, Xiaoyi Fu, Yu Liu, Zhenqian Shen","submitted_at":"2026-06-30T03:19:33Z","abstract_excerpt":"Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms. We propose DDIAgents, a mechanism-conditioned multi-agent framework that performs DDI prediction through dynamic knowledge orchestration. Given a drug pair, a planner agent instantiates specialized expert agents, routes mechanism-relevant knowledge sources to each agent, and aggregates their analyses through a conclusion agent. By adapting context flow to the inferred interaction mechanism, DDIAgents r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31085","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/2606.31085/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":"2606.31085","created_at":"2026-07-01T01:17:28.611460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31085v1","created_at":"2026-07-01T01:17:28.611460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31085","created_at":"2026-07-01T01:17:28.611460+00:00"},{"alias_kind":"pith_short_12","alias_value":"EV5B7ZTOSLCP","created_at":"2026-07-01T01:17:28.611460+00:00"},{"alias_kind":"pith_short_16","alias_value":"EV5B7ZTOSLCPBA32","created_at":"2026-07-01T01:17:28.611460+00:00"},{"alias_kind":"pith_short_8","alias_value":"EV5B7ZTO","created_at":"2026-07-01T01:17:28.611460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS","json":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS.json","graph_json":"https://pith.science/api/pith-number/EV5B7ZTOSLCPBA32K6MLWH7SHS/graph.json","events_json":"https://pith.science/api/pith-number/EV5B7ZTOSLCPBA32K6MLWH7SHS/events.json","paper":"https://pith.science/paper/EV5B7ZTO"},"agent_actions":{"view_html":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS","download_json":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS.json","view_paper":"https://pith.science/paper/EV5B7ZTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31085&json=true","fetch_graph":"https://pith.science/api/pith-number/EV5B7ZTOSLCPBA32K6MLWH7SHS/graph.json","fetch_events":"https://pith.science/api/pith-number/EV5B7ZTOSLCPBA32K6MLWH7SHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS/action/storage_attestation","attest_author":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS/action/author_attestation","sign_citation":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS/action/citation_signature","submit_replication":"https://pith.science/pith/EV5B7ZTOSLCPBA32K6MLWH7SHS/action/replication_record"}},"created_at":"2026-07-01T01:17:28.611460+00:00","updated_at":"2026-07-01T01:17:28.611460+00:00"}