{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IT2GD6TBP23FJ7VBXU7JLEFEVZ","short_pith_number":"pith:IT2GD6TB","schema_version":"1.0","canonical_sha256":"44f461fa617eb654fea1bd3e9590a4ae41d437cc21cc9413af6e68fd773c1bc1","source":{"kind":"arxiv","id":"2607.09322","version":1},"attestation_state":"computed","paper":{"title":"LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongxia Xu, Weiqi Zhai, Xiaocheng Zhang, Yanzhen Chen, Zhiting Fan, Zihan Xu, Zuozhu Liu","submitted_at":"2026-07-10T12:04:31Z","abstract_excerpt":"In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and tool use. However, real-world medical care is inherently longitudinal, and clinicians must aggregate evidence across repeated visits, tests, and evolving treatments. Therefore, long-horizon interaction is essential for realistic assessment. LongMedBench is constructed via a reproducible pipeline that integrates MIMIC-IV admission records and clinical notes into time-series event "},"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":"2607.09322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T12:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"648c9f0bf81196fc583ad4f319bf7de1ee1df0ff480596ec2fe802f6ae9cab93","abstract_canon_sha256":"d09fc8c21821920d28a77aea3098b1d168552b2ffc520bf6c6b35160d401b76c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:02.339414Z","signature_b64":"lss3Ibn2J2N9snwE9Pp+ohaLrPNDUCtOvixXwvQGIUaM0qiDYICKfJi4arC1NP1suxPQKMmeQWyOPKSCvCHVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44f461fa617eb654fea1bd3e9590a4ae41d437cc21cc9413af6e68fd773c1bc1","last_reissued_at":"2026-07-13T01:19:02.338243Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:02.338243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongxia Xu, Weiqi Zhai, Xiaocheng Zhang, Yanzhen Chen, Zhiting Fan, Zihan Xu, Zuozhu Liu","submitted_at":"2026-07-10T12:04:31Z","abstract_excerpt":"In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and tool use. However, real-world medical care is inherently longitudinal, and clinicians must aggregate evidence across repeated visits, tests, and evolving treatments. Therefore, long-horizon interaction is essential for realistic assessment. LongMedBench is constructed via a reproducible pipeline that integrates MIMIC-IV admission records and clinical notes into time-series event "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09322","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/2607.09322/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":"2607.09322","created_at":"2026-07-13T01:19:02.338778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09322v1","created_at":"2026-07-13T01:19:02.338778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09322","created_at":"2026-07-13T01:19:02.338778+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT2GD6TBP23F","created_at":"2026-07-13T01:19:02.338778+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT2GD6TBP23FJ7VB","created_at":"2026-07-13T01:19:02.338778+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT2GD6TB","created_at":"2026-07-13T01:19:02.338778+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/IT2GD6TBP23FJ7VBXU7JLEFEVZ","json":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ.json","graph_json":"https://pith.science/api/pith-number/IT2GD6TBP23FJ7VBXU7JLEFEVZ/graph.json","events_json":"https://pith.science/api/pith-number/IT2GD6TBP23FJ7VBXU7JLEFEVZ/events.json","paper":"https://pith.science/paper/IT2GD6TB"},"agent_actions":{"view_html":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ","download_json":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ.json","view_paper":"https://pith.science/paper/IT2GD6TB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09322&json=true","fetch_graph":"https://pith.science/api/pith-number/IT2GD6TBP23FJ7VBXU7JLEFEVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IT2GD6TBP23FJ7VBXU7JLEFEVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ/action/storage_attestation","attest_author":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ/action/author_attestation","sign_citation":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ/action/citation_signature","submit_replication":"https://pith.science/pith/IT2GD6TBP23FJ7VBXU7JLEFEVZ/action/replication_record"}},"created_at":"2026-07-13T01:19:02.338778+00:00","updated_at":"2026-07-13T01:19:02.338778+00:00"}