{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ML6K4OUM3RPPQQTOFEXI6DWFBK","short_pith_number":"pith:ML6K4OUM","schema_version":"1.0","canonical_sha256":"62fcae3a8cdc5ef8426e292e8f0ec50a904040dc3245ae2a6b2062e823948ba4","source":{"kind":"arxiv","id":"2505.19213","version":1},"attestation_state":"computed","paper":{"title":"Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kaitao Chen, Shaohao Rui, Weijie Ma, Xiaosong Wang","submitted_at":"2025-05-25T16:20:55Z","abstract_excerpt":"Recent advances in reinforcement learning with verifiable, rule-based rewards have greatly enhanced the reasoning capabilities and out-of-distribution generalization of VLMs/LLMs, obviating the need for manually crafted reasoning chains. Despite these promising developments in the general domain, their translation to medical imaging remains limited. Current medical reinforcement fine-tuning (RFT) methods predominantly focus on close-ended VQA, thereby restricting the model's ability to engage in world knowledge retrieval and flexible task adaptation. More critically, these methods fall short o"},"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":"2505.19213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-25T16:20:55Z","cross_cats_sorted":[],"title_canon_sha256":"8bfdc1b9a1076d6ecdb3d62268a117aa8cd7e6db96be8dd676c4df36472781ad","abstract_canon_sha256":"721e316bb8890277164a9c3695cc9c810af3958daa496e6ba1b1fb56541ca810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:26.535817Z","signature_b64":"XIFnhh1Bgm5qUoI9a80197cqaOVoiNsSYzZCGHQXZ60DCEm7oR+enm5CSJb6ODUHYjkGETmOoke2J82KfrNpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62fcae3a8cdc5ef8426e292e8f0ec50a904040dc3245ae2a6b2062e823948ba4","last_reissued_at":"2026-07-05T11:09:26.535322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:26.535322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kaitao Chen, Shaohao Rui, Weijie Ma, Xiaosong Wang","submitted_at":"2025-05-25T16:20:55Z","abstract_excerpt":"Recent advances in reinforcement learning with verifiable, rule-based rewards have greatly enhanced the reasoning capabilities and out-of-distribution generalization of VLMs/LLMs, obviating the need for manually crafted reasoning chains. Despite these promising developments in the general domain, their translation to medical imaging remains limited. Current medical reinforcement fine-tuning (RFT) methods predominantly focus on close-ended VQA, thereby restricting the model's ability to engage in world knowledge retrieval and flexible task adaptation. More critically, these methods fall short o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19213","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/2505.19213/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":"2505.19213","created_at":"2026-07-05T11:09:26.535384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19213v1","created_at":"2026-07-05T11:09:26.535384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19213","created_at":"2026-07-05T11:09:26.535384+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML6K4OUM3RPP","created_at":"2026-07-05T11:09:26.535384+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML6K4OUM3RPPQQTO","created_at":"2026-07-05T11:09:26.535384+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML6K4OUM","created_at":"2026-07-05T11:09:26.535384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31599","citing_title":"Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK","json":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK.json","graph_json":"https://pith.science/api/pith-number/ML6K4OUM3RPPQQTOFEXI6DWFBK/graph.json","events_json":"https://pith.science/api/pith-number/ML6K4OUM3RPPQQTOFEXI6DWFBK/events.json","paper":"https://pith.science/paper/ML6K4OUM"},"agent_actions":{"view_html":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK","download_json":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK.json","view_paper":"https://pith.science/paper/ML6K4OUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19213&json=true","fetch_graph":"https://pith.science/api/pith-number/ML6K4OUM3RPPQQTOFEXI6DWFBK/graph.json","fetch_events":"https://pith.science/api/pith-number/ML6K4OUM3RPPQQTOFEXI6DWFBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK/action/storage_attestation","attest_author":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK/action/author_attestation","sign_citation":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK/action/citation_signature","submit_replication":"https://pith.science/pith/ML6K4OUM3RPPQQTOFEXI6DWFBK/action/replication_record"}},"created_at":"2026-07-05T11:09:26.535384+00:00","updated_at":"2026-07-05T11:09:26.535384+00:00"}