{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VAFZVB45ITEQ7NZSEVHHSBVX3P","short_pith_number":"pith:VAFZVB45","schema_version":"1.0","canonical_sha256":"a80b9a879d44c90fb732254e7906b7dbd8af351f33988fa02d1d19c53d3465c0","source":{"kind":"arxiv","id":"2506.12849","version":1},"attestation_state":"computed","paper":{"title":"CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Lei, Jian Wu, Jimeng Sun, Ruilin Luo, Ruizhe Chen, Sibo Song, Songtao Jiang, Yang Feng, Yan Zhang, Yuan Wang, Zuozhu Liu","submitted_at":"2025-06-15T13:42:46Z","abstract_excerpt":"In medical visual question answering (Med-VQA), achieving accurate responses relies on three critical steps: precise perception of medical imaging data, logical reasoning grounded in visual input and textual questions, and coherent answer derivation from the reasoning process. Recent advances in general vision-language models (VLMs) show that large-scale reinforcement learning (RL) could significantly enhance both reasoning capabilities and overall model performance. However, their application in medical domains is hindered by two fundamental challenges: 1) misalignment between perceptual unde"},"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":"2506.12849","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-15T13:42:46Z","cross_cats_sorted":[],"title_canon_sha256":"d0bf0f38ea7ed2ec5e5dc8a8459be9c541d7628ed60cbd77eac9c2590796715a","abstract_canon_sha256":"84f2349eb7dbfa5a87957f1ada700f0fc721c855129f5ae270770474fb22d1af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:01.346889Z","signature_b64":"8Q3WJGbTGWiwwwNy/XdGg3ZRBTlgnWOxsRFjDTp79fYktt/1NWsTIILKWmYhhhfy230RcBs7JFdIPFYxpbQqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a80b9a879d44c90fb732254e7906b7dbd8af351f33988fa02d1d19c53d3465c0","last_reissued_at":"2026-07-05T11:22:01.346365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:01.346365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Lei, Jian Wu, Jimeng Sun, Ruilin Luo, Ruizhe Chen, Sibo Song, Songtao Jiang, Yang Feng, Yan Zhang, Yuan Wang, Zuozhu Liu","submitted_at":"2025-06-15T13:42:46Z","abstract_excerpt":"In medical visual question answering (Med-VQA), achieving accurate responses relies on three critical steps: precise perception of medical imaging data, logical reasoning grounded in visual input and textual questions, and coherent answer derivation from the reasoning process. Recent advances in general vision-language models (VLMs) show that large-scale reinforcement learning (RL) could significantly enhance both reasoning capabilities and overall model performance. However, their application in medical domains is hindered by two fundamental challenges: 1) misalignment between perceptual unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12849","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/2506.12849/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":"2506.12849","created_at":"2026-07-05T11:22:01.346424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12849v1","created_at":"2026-07-05T11:22:01.346424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12849","created_at":"2026-07-05T11:22:01.346424+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAFZVB45ITEQ","created_at":"2026-07-05T11:22:01.346424+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAFZVB45ITEQ7NZS","created_at":"2026-07-05T11:22:01.346424+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAFZVB45","created_at":"2026-07-05T11:22:01.346424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18687","citing_title":"Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P","json":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P.json","graph_json":"https://pith.science/api/pith-number/VAFZVB45ITEQ7NZSEVHHSBVX3P/graph.json","events_json":"https://pith.science/api/pith-number/VAFZVB45ITEQ7NZSEVHHSBVX3P/events.json","paper":"https://pith.science/paper/VAFZVB45"},"agent_actions":{"view_html":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P","download_json":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P.json","view_paper":"https://pith.science/paper/VAFZVB45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12849&json=true","fetch_graph":"https://pith.science/api/pith-number/VAFZVB45ITEQ7NZSEVHHSBVX3P/graph.json","fetch_events":"https://pith.science/api/pith-number/VAFZVB45ITEQ7NZSEVHHSBVX3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P/action/storage_attestation","attest_author":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P/action/author_attestation","sign_citation":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P/action/citation_signature","submit_replication":"https://pith.science/pith/VAFZVB45ITEQ7NZSEVHHSBVX3P/action/replication_record"}},"created_at":"2026-07-05T11:22:01.346424+00:00","updated_at":"2026-07-05T11:22:01.346424+00:00"}