{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BWSGYWZCDQLAAMBNYRVOJPDKR7","short_pith_number":"pith:BWSGYWZC","schema_version":"1.0","canonical_sha256":"0da46c5b221c1600302dc46ae4bc6a8fe04fdf7a8f71d7a9303bce4311087c45","source":{"kind":"arxiv","id":"2406.12036","version":4},"attestation_state":"computed","paper":{"title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","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","submitted_at":"2024-06-17T19:07:21Z","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"},"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":"2406.12036","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:07:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4531f3722059d98af6e7b33655bbbfc3fede2dbec98663f2f6530da26852cbdd","abstract_canon_sha256":"b5a926aecdf5884c63e394900ce5aedb078598751a6e9b081b9aec0d91a4ba45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:11.270667Z","signature_b64":"xhnZkvBunrK5f9eWx52hGQE9k0R2shZyDnG+hLUgI5sxJUnT1K9SaJJW5YeAiDrMcSsWZsRzNLWIqM6JJBKyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0da46c5b221c1600302dc46ae4bc6a8fe04fdf7a8f71d7a9303bce4311087c45","last_reissued_at":"2026-07-05T08:38:11.270154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:11.270154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","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","submitted_at":"2024-06-17T19:07:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12036","kind":"arxiv","version":4},"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/2406.12036/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":"2406.12036","created_at":"2026-07-05T08:38:11.270221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12036v4","created_at":"2026-07-05T08:38:11.270221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12036","created_at":"2026-07-05T08:38:11.270221+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWSGYWZCDQLA","created_at":"2026-07-05T08:38:11.270221+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWSGYWZCDQLAAMBN","created_at":"2026-07-05T08:38:11.270221+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWSGYWZC","created_at":"2026-07-05T08:38:11.270221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10217","citing_title":"Alignment Defends LLMs from Property Inference Attacks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16679","citing_title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7","json":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7.json","graph_json":"https://pith.science/api/pith-number/BWSGYWZCDQLAAMBNYRVOJPDKR7/graph.json","events_json":"https://pith.science/api/pith-number/BWSGYWZCDQLAAMBNYRVOJPDKR7/events.json","paper":"https://pith.science/paper/BWSGYWZC"},"agent_actions":{"view_html":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7","download_json":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7.json","view_paper":"https://pith.science/paper/BWSGYWZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12036&json=true","fetch_graph":"https://pith.science/api/pith-number/BWSGYWZCDQLAAMBNYRVOJPDKR7/graph.json","fetch_events":"https://pith.science/api/pith-number/BWSGYWZCDQLAAMBNYRVOJPDKR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7/action/storage_attestation","attest_author":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7/action/author_attestation","sign_citation":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7/action/citation_signature","submit_replication":"https://pith.science/pith/BWSGYWZCDQLAAMBNYRVOJPDKR7/action/replication_record"}},"created_at":"2026-07-05T08:38:11.270221+00:00","updated_at":"2026-07-05T08:38:11.270221+00:00"}