{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BWSGYWZCDQLAAMBNYRVOJPDKR7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b5a926aecdf5884c63e394900ce5aedb078598751a6e9b081b9aec0d91a4ba45","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:07:21Z","title_canon_sha256":"4531f3722059d98af6e7b33655bbbfc3fede2dbec98663f2f6530da26852cbdd"},"schema_version":"1.0","source":{"id":"2406.12036","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12036","created_at":"2026-07-05T08:38:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12036v4","created_at":"2026-07-05T08:38:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12036","created_at":"2026-07-05T08:38:11Z"},{"alias_kind":"pith_short_12","alias_value":"BWSGYWZCDQLA","created_at":"2026-07-05T08:38:11Z"},{"alias_kind":"pith_short_16","alias_value":"BWSGYWZCDQLAAMBN","created_at":"2026-07-05T08:38:11Z"},{"alias_kind":"pith_short_8","alias_value":"BWSGYWZC","created_at":"2026-07-05T08:38:11Z"}],"graph_snapshots":[{"event_id":"sha256:846b9b23a4a0a706200a930807e586db47d83bb9aaebbc56ef33aed34b6726e0","target":"graph","created_at":"2026-07-05T08:38:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.12036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As opposed to evaluating computation and logic-based reasoning, current benchmarks for evaluating large language models (LLMs) in medicine are primarily focused on question-answering involving domain knowledge and descriptive reasoning. While such qualitative capabilities are vital to medical diagnosis, in real-world scenarios, doctors frequently use clinical calculators that follow quantitative equations and rule-based reasoning paradigms for evidence-based decision support. To this end, we propose MedCalc-Bench, a first-of-its-kind dataset focused on evaluating the medical calculation capabi","authors_text":"Abid A Anwar, Aidan Gilson, Aidong Zhang, Amisha Dave, Andrew Taylor, Andrew Zhang, Conrad W Safranek, Guangzhi Xiong, Maame Sarfo-Gyamfi, Maxwell B Singer, Nikhil Khandekar, Qiao Jin, Qingyu Chen, Serina S Applebaum, Soren Dunn, Zain Anwar, Zhiyong Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:07:21Z","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12036","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:93351243e615cd57887c3e13289b34f4e5611ead308ce15700002af6e49a82a7","target":"record","created_at":"2026-07-05T08:38:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b5a926aecdf5884c63e394900ce5aedb078598751a6e9b081b9aec0d91a4ba45","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:07:21Z","title_canon_sha256":"4531f3722059d98af6e7b33655bbbfc3fede2dbec98663f2f6530da26852cbdd"},"schema_version":"1.0","source":{"id":"2406.12036","kind":"arxiv","version":4}},"canonical_sha256":"0da46c5b221c1600302dc46ae4bc6a8fe04fdf7a8f71d7a9303bce4311087c45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0da46c5b221c1600302dc46ae4bc6a8fe04fdf7a8f71d7a9303bce4311087c45","first_computed_at":"2026-07-05T08:38:11.270154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:11.270154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xhnZkvBunrK5f9eWx52hGQE9k0R2shZyDnG+hLUgI5sxJUnT1K9SaJJW5YeAiDrMcSsWZsRzNLWIqM6JJBKyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:11.270667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12036","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93351243e615cd57887c3e13289b34f4e5611ead308ce15700002af6e49a82a7","sha256:846b9b23a4a0a706200a930807e586db47d83bb9aaebbc56ef33aed34b6726e0"],"state_sha256":"f426137bcb047f0dc25d50ef1b10a2d14e8bb5141dd7370c758aa0ad3bdb11f2"}