{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GHOKCR7PBQVCZMOBOOXQLWVSIS","short_pith_number":"pith:GHOKCR7P","schema_version":"1.0","canonical_sha256":"31dca147ef0c2a2cb1c173af05dab244b6dffd53669d529366721d44f0d93fc0","source":{"kind":"arxiv","id":"2607.02879","version":1},"attestation_state":"computed","paper":{"title":"MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chennuo Zhang, Ruihui Hou, Siran Zhao, Tong Ruan, Ziyue Huai","submitted_at":"2026-07-03T02:24:26Z","abstract_excerpt":"Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query. However, real clinical scenarios often require multiple calculators for joint evaluation, nested-scale calculation, and fuzzy queries that do not directly specify the target calculator. To this end, we propose a new medical calculation benchmark, MedCalc-Pro, which covers three progressively challenging task settings: single-calculator, multi-calculat"},"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":"2607.02879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-03T02:24:26Z","cross_cats_sorted":[],"title_canon_sha256":"1a90e166c841000aa047fe4eb0198f0fdcddac36bcc7315a0246049ba7372ab5","abstract_canon_sha256":"4459ac00d5c249745558f0be6484a4407b17f95a2897a6f6c3b006375be31ada"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:35.185861Z","signature_b64":"ILO0b32swoKKxGDAhx5kqKo+PSssDpWljKViK9GsMv0R0zf5g/H2bzDu1V3907wEJSLNpo1kHdgSYyr0mIGRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31dca147ef0c2a2cb1c173af05dab244b6dffd53669d529366721d44f0d93fc0","last_reissued_at":"2026-07-07T01:16:35.185271Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:35.185271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chennuo Zhang, Ruihui Hou, Siran Zhao, Tong Ruan, Ziyue Huai","submitted_at":"2026-07-03T02:24:26Z","abstract_excerpt":"Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query. However, real clinical scenarios often require multiple calculators for joint evaluation, nested-scale calculation, and fuzzy queries that do not directly specify the target calculator. To this end, we propose a new medical calculation benchmark, MedCalc-Pro, which covers three progressively challenging task settings: single-calculator, multi-calculat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02879","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/2607.02879/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":"2607.02879","created_at":"2026-07-07T01:16:35.185363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02879v1","created_at":"2026-07-07T01:16:35.185363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02879","created_at":"2026-07-07T01:16:35.185363+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHOKCR7PBQVC","created_at":"2026-07-07T01:16:35.185363+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHOKCR7PBQVCZMOB","created_at":"2026-07-07T01:16:35.185363+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHOKCR7P","created_at":"2026-07-07T01:16:35.185363+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/GHOKCR7PBQVCZMOBOOXQLWVSIS","json":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS.json","graph_json":"https://pith.science/api/pith-number/GHOKCR7PBQVCZMOBOOXQLWVSIS/graph.json","events_json":"https://pith.science/api/pith-number/GHOKCR7PBQVCZMOBOOXQLWVSIS/events.json","paper":"https://pith.science/paper/GHOKCR7P"},"agent_actions":{"view_html":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS","download_json":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS.json","view_paper":"https://pith.science/paper/GHOKCR7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02879&json=true","fetch_graph":"https://pith.science/api/pith-number/GHOKCR7PBQVCZMOBOOXQLWVSIS/graph.json","fetch_events":"https://pith.science/api/pith-number/GHOKCR7PBQVCZMOBOOXQLWVSIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS/action/storage_attestation","attest_author":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS/action/author_attestation","sign_citation":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS/action/citation_signature","submit_replication":"https://pith.science/pith/GHOKCR7PBQVCZMOBOOXQLWVSIS/action/replication_record"}},"created_at":"2026-07-07T01:16:35.185363+00:00","updated_at":"2026-07-07T01:16:35.185363+00:00"}