{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y5SSZQCH2CJDIYG5PCYBCN26QG","short_pith_number":"pith:Y5SSZQCH","schema_version":"1.0","canonical_sha256":"c7652cc047d0923460dd78b011375e818c52ef7faf6ea8e90d70d1e0868e2e8a","source":{"kind":"arxiv","id":"2606.03157","version":1},"attestation_state":"computed","paper":{"title":"ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunming Wang, Guangya Yu, Ruihui Hou, Siyi Zhu, Tong Ruan, Yongqi Fan, Ziyue Huai","submitted_at":"2026-06-02T05:09:18Z","abstract_excerpt":"Large language models (LLMs) have been widely adopted in healthcare, yet they still encounter significant challenges in complex clinical decision-making scenarios. Existing benchmarks primarily assess LLM performance in single-course settings and lack systematic evaluation in multi-course scenarios, where a patient's condition evolves over time. To address this gap, we propose ClinicalMC, a benchmark for multi-course clinical decision-making. It includes 1,275 Chinese and 5,804 English samples across four stages from admission to discharge. These stages cover triage, first-course examination/d"},"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":"2606.03157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T05:09:18Z","cross_cats_sorted":[],"title_canon_sha256":"6b77c110e1e8ff33ee835dbfa9e9945672c95311e7d668473dfc79400a1613c4","abstract_canon_sha256":"e6eb3d6ceab4240b3247d5a11045aca731fae018ff17777b7d39911360f374eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:33.468169Z","signature_b64":"3B0wDInekoF9s7NShxbZk6DUg2kxMuDWs55gDs6iV8s+kBn+9LB43yS8HkYuYHUuZFWCMEcEbwXgcYZQeIk5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7652cc047d0923460dd78b011375e818c52ef7faf6ea8e90d70d1e0868e2e8a","last_reissued_at":"2026-06-03T01:05:33.467770Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:33.467770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunming Wang, Guangya Yu, Ruihui Hou, Siyi Zhu, Tong Ruan, Yongqi Fan, Ziyue Huai","submitted_at":"2026-06-02T05:09:18Z","abstract_excerpt":"Large language models (LLMs) have been widely adopted in healthcare, yet they still encounter significant challenges in complex clinical decision-making scenarios. Existing benchmarks primarily assess LLM performance in single-course settings and lack systematic evaluation in multi-course scenarios, where a patient's condition evolves over time. To address this gap, we propose ClinicalMC, a benchmark for multi-course clinical decision-making. It includes 1,275 Chinese and 5,804 English samples across four stages from admission to discharge. These stages cover triage, first-course examination/d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03157","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/2606.03157/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":"2606.03157","created_at":"2026-06-03T01:05:33.467827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03157v1","created_at":"2026-06-03T01:05:33.467827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03157","created_at":"2026-06-03T01:05:33.467827+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5SSZQCH2CJD","created_at":"2026-06-03T01:05:33.467827+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5SSZQCH2CJDIYG5","created_at":"2026-06-03T01:05:33.467827+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5SSZQCH","created_at":"2026-06-03T01:05:33.467827+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/Y5SSZQCH2CJDIYG5PCYBCN26QG","json":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG.json","graph_json":"https://pith.science/api/pith-number/Y5SSZQCH2CJDIYG5PCYBCN26QG/graph.json","events_json":"https://pith.science/api/pith-number/Y5SSZQCH2CJDIYG5PCYBCN26QG/events.json","paper":"https://pith.science/paper/Y5SSZQCH"},"agent_actions":{"view_html":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG","download_json":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG.json","view_paper":"https://pith.science/paper/Y5SSZQCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03157&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5SSZQCH2CJDIYG5PCYBCN26QG/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5SSZQCH2CJDIYG5PCYBCN26QG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG/action/storage_attestation","attest_author":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG/action/author_attestation","sign_citation":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG/action/citation_signature","submit_replication":"https://pith.science/pith/Y5SSZQCH2CJDIYG5PCYBCN26QG/action/replication_record"}},"created_at":"2026-06-03T01:05:33.467827+00:00","updated_at":"2026-06-03T01:05:33.467827+00:00"}