{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DEGPIYU5BD2EEZEKWEW3P6JL7A","short_pith_number":"pith:DEGPIYU5","schema_version":"1.0","canonical_sha256":"190cf4629d08f442648ab12db7f92bf8370b4a7aa660fb0ac51f86213d324307","source":{"kind":"arxiv","id":"2607.25186","version":1},"attestation_state":"computed","paper":{"title":"MyoCardBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Xu, Jingru Ding, Juechen Chen, Junbo Ge, Lu Lu, Mouxiao Bian, Sijie Ren, Xiao Li, Yixiu Liang, Yun Zhong, Zhaodi Wu","submitted_at":"2026-07-28T01:39:52Z","abstract_excerpt":"Background: Most medical large language model (LLM) benchmarks focus on examination knowledge or isolated tasks and may not reflect the longitudinal, multimodal, and safety-critical workflow of cardiovascular care. Objective: To develop MyoCardBench, a real-world benchmark spanning the cardiovascular care continuum, and assess LLM performance across clinical dimensions and specialist tasks. Methods: MyoCardBench includes 2,263 items from 13 task-specific datasets derived from de-identified cardiovascular records and examination data. Sixteen cardiology physicians conducted annotation and refer"},"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":"2607.25186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T01:39:52Z","cross_cats_sorted":[],"title_canon_sha256":"9db73ebca6a2f101527fb7daf2fcb571e0b37c1b87a0ad87c431c284cf31c4d0","abstract_canon_sha256":"71c7d6b403f0e33e5c4c38b9299dd77a049e242ecfe6897bf0dcb18b3e80a396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:07.526267Z","signature_b64":"8qgGiIFW6t7a6GyVtxQqgqWrMnT2Y60k8fLbIKDlXsTZ38hO59B3766cWTH1Vcmwwj1vjySxF1HhLMr1Z2wpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"190cf4629d08f442648ab12db7f92bf8370b4a7aa660fb0ac51f86213d324307","last_reissued_at":"2026-07-29T00:25:07.525422Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:07.525422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MyoCardBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Xu, Jingru Ding, Juechen Chen, Junbo Ge, Lu Lu, Mouxiao Bian, Sijie Ren, Xiao Li, Yixiu Liang, Yun Zhong, Zhaodi Wu","submitted_at":"2026-07-28T01:39:52Z","abstract_excerpt":"Background: Most medical large language model (LLM) benchmarks focus on examination knowledge or isolated tasks and may not reflect the longitudinal, multimodal, and safety-critical workflow of cardiovascular care. Objective: To develop MyoCardBench, a real-world benchmark spanning the cardiovascular care continuum, and assess LLM performance across clinical dimensions and specialist tasks. Methods: MyoCardBench includes 2,263 items from 13 task-specific datasets derived from de-identified cardiovascular records and examination data. Sixteen cardiology physicians conducted annotation and refer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25186","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/2607.25186/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":"2607.25186","created_at":"2026-07-29T00:25:07.525866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25186v1","created_at":"2026-07-29T00:25:07.525866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25186","created_at":"2026-07-29T00:25:07.525866+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEGPIYU5BD2E","created_at":"2026-07-29T00:25:07.525866+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEGPIYU5BD2EEZEK","created_at":"2026-07-29T00:25:07.525866+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEGPIYU5","created_at":"2026-07-29T00:25:07.525866+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/DEGPIYU5BD2EEZEKWEW3P6JL7A","json":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A.json","graph_json":"https://pith.science/api/pith-number/DEGPIYU5BD2EEZEKWEW3P6JL7A/graph.json","events_json":"https://pith.science/api/pith-number/DEGPIYU5BD2EEZEKWEW3P6JL7A/events.json","paper":"https://pith.science/paper/DEGPIYU5"},"agent_actions":{"view_html":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A","download_json":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A.json","view_paper":"https://pith.science/paper/DEGPIYU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25186&json=true","fetch_graph":"https://pith.science/api/pith-number/DEGPIYU5BD2EEZEKWEW3P6JL7A/graph.json","fetch_events":"https://pith.science/api/pith-number/DEGPIYU5BD2EEZEKWEW3P6JL7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A/action/storage_attestation","attest_author":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A/action/author_attestation","sign_citation":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A/action/citation_signature","submit_replication":"https://pith.science/pith/DEGPIYU5BD2EEZEKWEW3P6JL7A/action/replication_record"}},"created_at":"2026-07-29T00:25:07.525866+00:00","updated_at":"2026-07-29T00:25:07.525866+00:00"}