{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWPC3EWHSZZSP3N4OOW43G43C7","short_pith_number":"pith:LWPC3EWH","schema_version":"1.0","canonical_sha256":"5d9e2d92c7967327edbc73adcd9b9b17ee4c57d81d2a7684ba084c77f27c6166","source":{"kind":"arxiv","id":"2410.04660","version":2},"attestation_state":"computed","paper":{"title":"KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Djork-Arn\\'e Clevert, Marinka Zitnik, Shanghua Gao, Valentina Giunchiglia, Xiaolong Liu, Xiaorui Su, Yibo Wang","submitted_at":"2024-10-07T00:17:37Z","abstract_excerpt":"Biomedical reasoning integrates structured, codified knowledge with tacit, experience-driven insights. Depending on the context, quantity, and nature of available evidence, researchers and clinicians use diverse strategies, including rule-based, prototype-based, and case-based reasoning. Effective medical AI models must handle this complexity while ensuring reliability and adaptability. We introduce KGARevion, a knowledge graph-based agent that answers knowledge-intensive questions. Upon receiving a query, KGARevion generates relevant triplets by leveraging the latent knowledge embedded in a l"},"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":"2410.04660","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-07T00:17:37Z","cross_cats_sorted":[],"title_canon_sha256":"88302726bfc1c5ae0d4b752e1be31b72841edb52f31a628531d6fa8331c71051","abstract_canon_sha256":"64609e33d1d183dcbb871495e09a592d9fa3a1fda8834ac53621160c2f6d2a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:51.693407Z","signature_b64":"AxoxiUnWf0g9Mdiabjc+WonJOAi1+8OQ4otOgUc+Wn67tkBO9uPQ1otuoDCxGmpfffP+d3ttD0DXfhbmqH2VDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9e2d92c7967327edbc73adcd9b9b17ee4c57d81d2a7684ba084c77f27c6166","last_reissued_at":"2026-07-05T10:22:51.692784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:51.692784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Djork-Arn\\'e Clevert, Marinka Zitnik, Shanghua Gao, Valentina Giunchiglia, Xiaolong Liu, Xiaorui Su, Yibo Wang","submitted_at":"2024-10-07T00:17:37Z","abstract_excerpt":"Biomedical reasoning integrates structured, codified knowledge with tacit, experience-driven insights. Depending on the context, quantity, and nature of available evidence, researchers and clinicians use diverse strategies, including rule-based, prototype-based, and case-based reasoning. Effective medical AI models must handle this complexity while ensuring reliability and adaptability. We introduce KGARevion, a knowledge graph-based agent that answers knowledge-intensive questions. Upon receiving a query, KGARevion generates relevant triplets by leveraging the latent knowledge embedded in a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04660","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/2410.04660/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":"2410.04660","created_at":"2026-07-05T10:22:51.692860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04660v2","created_at":"2026-07-05T10:22:51.692860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04660","created_at":"2026-07-05T10:22:51.692860+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWPC3EWHSZZS","created_at":"2026-07-05T10:22:51.692860+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWPC3EWHSZZSP3N4","created_at":"2026-07-05T10:22:51.692860+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWPC3EWH","created_at":"2026-07-05T10:22:51.692860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27269","citing_title":"Unifying biomedical knowledge in a modern multimodal graph","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7","json":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7.json","graph_json":"https://pith.science/api/pith-number/LWPC3EWHSZZSP3N4OOW43G43C7/graph.json","events_json":"https://pith.science/api/pith-number/LWPC3EWHSZZSP3N4OOW43G43C7/events.json","paper":"https://pith.science/paper/LWPC3EWH"},"agent_actions":{"view_html":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7","download_json":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7.json","view_paper":"https://pith.science/paper/LWPC3EWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04660&json=true","fetch_graph":"https://pith.science/api/pith-number/LWPC3EWHSZZSP3N4OOW43G43C7/graph.json","fetch_events":"https://pith.science/api/pith-number/LWPC3EWHSZZSP3N4OOW43G43C7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7/action/storage_attestation","attest_author":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7/action/author_attestation","sign_citation":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7/action/citation_signature","submit_replication":"https://pith.science/pith/LWPC3EWHSZZSP3N4OOW43G43C7/action/replication_record"}},"created_at":"2026-07-05T10:22:51.692860+00:00","updated_at":"2026-07-05T10:22:51.692860+00:00"}