{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHOKCR7PBQVCZMOBOOXQLWVSIS","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":"4459ac00d5c249745558f0be6484a4407b17f95a2897a6f6c3b006375be31ada","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-03T02:24:26Z","title_canon_sha256":"1a90e166c841000aa047fe4eb0198f0fdcddac36bcc7315a0246049ba7372ab5"},"schema_version":"1.0","source":{"id":"2607.02879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02879","created_at":"2026-07-07T01:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02879v1","created_at":"2026-07-07T01:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02879","created_at":"2026-07-07T01:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"GHOKCR7PBQVC","created_at":"2026-07-07T01:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"GHOKCR7PBQVCZMOB","created_at":"2026-07-07T01:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"GHOKCR7P","created_at":"2026-07-07T01:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:c1e8137756490068d33ed8de6735ffc8125c603e32e3652f1fe2d4f0bda19435","target":"graph","created_at":"2026-07-07T01:16:35Z","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/2607.02879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chennuo Zhang, Ruihui Hou, Siran Zhao, Tong Ruan, Ziyue Huai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-03T02:24:26Z","title":"MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02879","kind":"arxiv","version":1},"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":"sha256:5ce2f3bc8b950ebb2b0a4c97e7ab632c2ee8154e3fd6aad981557e801dd8c1c3","target":"record","created_at":"2026-07-07T01:16:35Z","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":"4459ac00d5c249745558f0be6484a4407b17f95a2897a6f6c3b006375be31ada","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-03T02:24:26Z","title_canon_sha256":"1a90e166c841000aa047fe4eb0198f0fdcddac36bcc7315a0246049ba7372ab5"},"schema_version":"1.0","source":{"id":"2607.02879","kind":"arxiv","version":1}},"canonical_sha256":"31dca147ef0c2a2cb1c173af05dab244b6dffd53669d529366721d44f0d93fc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31dca147ef0c2a2cb1c173af05dab244b6dffd53669d529366721d44f0d93fc0","first_computed_at":"2026-07-07T01:16:35.185271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:35.185271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ILO0b32swoKKxGDAhx5kqKo+PSssDpWljKViK9GsMv0R0zf5g/H2bzDu1V3907wEJSLNpo1kHdgSYyr0mIGRAg==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:35.185861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ce2f3bc8b950ebb2b0a4c97e7ab632c2ee8154e3fd6aad981557e801dd8c1c3","sha256:c1e8137756490068d33ed8de6735ffc8125c603e32e3652f1fe2d4f0bda19435"],"state_sha256":"ee13b0d65198450d7ce9fa6688834ded6ed4f2490c339a263f9ff3d1a334d6e1"}