{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PEFAM6V2KNFLZ4KIEF2P6BTTH6","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":"3d3f98f5ff73414732e693d2aaad03f82981bd1adb17adba5bcd12be25ace9fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T10:13:20Z","title_canon_sha256":"e0cd4f5b3e00702003616bed6b1c341e1a5903690e8fbed2f31e33adc994cbeb"},"schema_version":"1.0","source":{"id":"2608.08623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08623","created_at":"2026-08-11T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08623v1","created_at":"2026-08-11T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08623","created_at":"2026-08-11T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"PEFAM6V2KNFL","created_at":"2026-08-11T01:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"PEFAM6V2KNFLZ4KI","created_at":"2026-08-11T01:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"PEFAM6V2","created_at":"2026-08-11T01:23:11Z"}],"graph_snapshots":[{"event_id":"sha256:cc8724b8bced490d45242024b8cfc1247db66ef8117110cdd5af963813e6eb2b","target":"graph","created_at":"2026-08-11T01:23:11Z","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/2608.08623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Reinforcement Learning with Verifiable Rewards (RLVR) frameworks for mathematical reasoning tasks, floating-point results are typically evaluated using a tolerance-based reward. However, this strategy suffers from challenges such as difficulty in threshold calibration, unstable training dynamics, and limited accuracy, especially in clinical scenarios. To address these limitations, we propose a knowledge-guided hybrid reward framework (\\textsc{MedCalc-R1}). Specifically, we introduce a knowledge verification reward mechanism that enforces explicit generation of computational formulas, which ","authors_text":"Fanshu Meng, Haotian Wang, Jingchi Jiang, Lian Yan, Xingzhi Yao, Ye He, Yi Guan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T10:13:20Z","title":"MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08623","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":"sha256:02ae2aaeecdca9fd3fc32a1cbcd56e774c122d06eaad06b8b43b29caa28b54d8","target":"record","created_at":"2026-08-11T01:23:11Z","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":"3d3f98f5ff73414732e693d2aaad03f82981bd1adb17adba5bcd12be25ace9fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T10:13:20Z","title_canon_sha256":"e0cd4f5b3e00702003616bed6b1c341e1a5903690e8fbed2f31e33adc994cbeb"},"schema_version":"1.0","source":{"id":"2608.08623","kind":"arxiv","version":1}},"canonical_sha256":"790a067aba534abcf1482174ff06733f9a9896bffb78a95c44605cca79d0a10c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"790a067aba534abcf1482174ff06733f9a9896bffb78a95c44605cca79d0a10c","first_computed_at":"2026-08-11T01:23:11.904176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:23:11.904176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RB2+30Vb6sdsB6nAX3jaB1HlJK2T5jllmwE1OE+2aE0yS4/V5YcDsZAgBLd4HA2veFe11kf9q/ujhG36TJzgDQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:23:11.906546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02ae2aaeecdca9fd3fc32a1cbcd56e774c122d06eaad06b8b43b29caa28b54d8","sha256:cc8724b8bced490d45242024b8cfc1247db66ef8117110cdd5af963813e6eb2b"],"state_sha256":"8e509e4343f12c030507d8c27cdb71f0f1ab86894e13bc478f4e272a942d5a6e"}