{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PEFAM6V2KNFLZ4KIEF2P6BTTH6","short_pith_number":"pith:PEFAM6V2","schema_version":"1.0","canonical_sha256":"790a067aba534abcf1482174ff06733f9a9896bffb78a95c44605cca79d0a10c","source":{"kind":"arxiv","id":"2608.08623","version":1},"attestation_state":"computed","paper":{"title":"MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fanshu Meng, Haotian Wang, Jingchi Jiang, Lian Yan, Xingzhi Yao, Ye He, Yi Guan","submitted_at":"2026-08-09T10:13:20Z","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 "},"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":"2608.08623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T10:13:20Z","cross_cats_sorted":[],"title_canon_sha256":"e0cd4f5b3e00702003616bed6b1c341e1a5903690e8fbed2f31e33adc994cbeb","abstract_canon_sha256":"3d3f98f5ff73414732e693d2aaad03f82981bd1adb17adba5bcd12be25ace9fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:11.906546Z","signature_b64":"RB2+30Vb6sdsB6nAX3jaB1HlJK2T5jllmwE1OE+2aE0yS4/V5YcDsZAgBLd4HA2veFe11kf9q/ujhG36TJzgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"790a067aba534abcf1482174ff06733f9a9896bffb78a95c44605cca79d0a10c","last_reissued_at":"2026-08-11T01:23:11.904176Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:11.904176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fanshu Meng, Haotian Wang, Jingchi Jiang, Lian Yan, Xingzhi Yao, Ye He, Yi Guan","submitted_at":"2026-08-09T10:13:20Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08623","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/2608.08623/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":"2608.08623","created_at":"2026-08-11T01:23:11.904965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08623v1","created_at":"2026-08-11T01:23:11.904965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08623","created_at":"2026-08-11T01:23:11.904965+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEFAM6V2KNFL","created_at":"2026-08-11T01:23:11.904965+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEFAM6V2KNFLZ4KI","created_at":"2026-08-11T01:23:11.904965+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEFAM6V2","created_at":"2026-08-11T01:23:11.904965+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/PEFAM6V2KNFLZ4KIEF2P6BTTH6","json":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6.json","graph_json":"https://pith.science/api/pith-number/PEFAM6V2KNFLZ4KIEF2P6BTTH6/graph.json","events_json":"https://pith.science/api/pith-number/PEFAM6V2KNFLZ4KIEF2P6BTTH6/events.json","paper":"https://pith.science/paper/PEFAM6V2"},"agent_actions":{"view_html":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6","download_json":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6.json","view_paper":"https://pith.science/paper/PEFAM6V2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08623&json=true","fetch_graph":"https://pith.science/api/pith-number/PEFAM6V2KNFLZ4KIEF2P6BTTH6/graph.json","fetch_events":"https://pith.science/api/pith-number/PEFAM6V2KNFLZ4KIEF2P6BTTH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6/action/storage_attestation","attest_author":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6/action/author_attestation","sign_citation":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6/action/citation_signature","submit_replication":"https://pith.science/pith/PEFAM6V2KNFLZ4KIEF2P6BTTH6/action/replication_record"}},"created_at":"2026-08-11T01:23:11.904965+00:00","updated_at":"2026-08-11T01:23:11.904965+00:00"}