{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YV6MKVRVBWFMD4JLZCTBAHTKGG","short_pith_number":"pith:YV6MKVRV","schema_version":"1.0","canonical_sha256":"c57cc556350d8ac1f12bc8a6101e6a31a08b820dc94cb8f5a0d1b457a24c181d","source":{"kind":"arxiv","id":"2606.25407","version":1},"attestation_state":"computed","paper":{"title":"Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Liu, Hui Guo, Jile Jiao, Xiaofeng Mou, Xiao Han, Yi Xu, Yue Wang, Zhimin Bao","submitted_at":"2026-06-24T05:07:41Z","abstract_excerpt":"Chest X-ray visual question answering (CXR VQA) requires models not only to predict correct answers, but also to produce reliable medical reasoning. However, existing reinforcement-learning-based training typically relies on answer-level rewards, which are often too coarse to improve chain-of-thought (CoT) quality and can become ineffective when group-level advantages collapse to zero. We propose \\textbf{Teach-to-Reason (T2R)}, a framework that introduces comparison-based supervision into CoT optimization through a self-improving \\emph{Teacher} and a competition-guided \\emph{Reasoner}. As the "},"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":"2606.25407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T05:07:41Z","cross_cats_sorted":[],"title_canon_sha256":"44354e955d2d78410514c77cbe890ab8f0083bb1e84f92d1472655b62a9eaf99","abstract_canon_sha256":"4300c1e888769b9f8fc90ff210150035bc32813ccf7018a496377782980d4bc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:04.551818Z","signature_b64":"QRgp2FiEBAOeyxHYdHIh0TgKr4zNgCNrywRaBosyOQO9tWfWVhswXGDyIBuHqaiJlW0R53vFmIvDomkyBsfhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c57cc556350d8ac1f12bc8a6101e6a31a08b820dc94cb8f5a0d1b457a24c181d","last_reissued_at":"2026-06-25T01:18:04.551416Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:04.551416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Liu, Hui Guo, Jile Jiao, Xiaofeng Mou, Xiao Han, Yi Xu, Yue Wang, Zhimin Bao","submitted_at":"2026-06-24T05:07:41Z","abstract_excerpt":"Chest X-ray visual question answering (CXR VQA) requires models not only to predict correct answers, but also to produce reliable medical reasoning. However, existing reinforcement-learning-based training typically relies on answer-level rewards, which are often too coarse to improve chain-of-thought (CoT) quality and can become ineffective when group-level advantages collapse to zero. We propose \\textbf{Teach-to-Reason (T2R)}, a framework that introduces comparison-based supervision into CoT optimization through a self-improving \\emph{Teacher} and a competition-guided \\emph{Reasoner}. As the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25407","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/2606.25407/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":"2606.25407","created_at":"2026-06-25T01:18:04.551481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25407v1","created_at":"2026-06-25T01:18:04.551481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25407","created_at":"2026-06-25T01:18:04.551481+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV6MKVRVBWFM","created_at":"2026-06-25T01:18:04.551481+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV6MKVRVBWFMD4JL","created_at":"2026-06-25T01:18:04.551481+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV6MKVRV","created_at":"2026-06-25T01:18:04.551481+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/YV6MKVRVBWFMD4JLZCTBAHTKGG","json":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG.json","graph_json":"https://pith.science/api/pith-number/YV6MKVRVBWFMD4JLZCTBAHTKGG/graph.json","events_json":"https://pith.science/api/pith-number/YV6MKVRVBWFMD4JLZCTBAHTKGG/events.json","paper":"https://pith.science/paper/YV6MKVRV"},"agent_actions":{"view_html":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG","download_json":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG.json","view_paper":"https://pith.science/paper/YV6MKVRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25407&json=true","fetch_graph":"https://pith.science/api/pith-number/YV6MKVRVBWFMD4JLZCTBAHTKGG/graph.json","fetch_events":"https://pith.science/api/pith-number/YV6MKVRVBWFMD4JLZCTBAHTKGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG/action/storage_attestation","attest_author":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG/action/author_attestation","sign_citation":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG/action/citation_signature","submit_replication":"https://pith.science/pith/YV6MKVRVBWFMD4JLZCTBAHTKGG/action/replication_record"}},"created_at":"2026-06-25T01:18:04.551481+00:00","updated_at":"2026-06-25T01:18:04.551481+00:00"}