{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NLBDJIXQPOCUVKEWMI6LGT6CGD","short_pith_number":"pith:NLBDJIXQ","schema_version":"1.0","canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","source":{"kind":"arxiv","id":"2607.10966","version":1},"attestation_state":"computed","paper":{"title":"SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aashu Singh, Fei Liu, Hanchao Yu, Jianyu Wang, Jingcheng Yang, Jize Jiang, Khoi Pham, Klara Nahrstedt, Mingyuan Wu, Qifan Wang, Shengyi Qian, Xudong Wang, Zhaolun Su, Zhuokai Zhao","submitted_at":"2026-07-13T00:21:30Z","abstract_excerpt":"We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the model proposes an answer using the same weights, and issues a binary self-verdict (Yes/No). A 'No' triggers a second-chance rethink; a 'Yes,' or a turn cap, finalizes the output for computing the outcome-based reward. SVR-R1 is implemented with GRPO and an asynchronous multi-turn rollout framework and needs no external supervision or auxiliary critics. We evaluate SVR-R1 on vision-language reasoning benchmarks and sho"},"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":"2607.10966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T00:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"2805ec4842bb440d5f384d8bf587562dfb571e01cc86b1ebdce17b08540fa102","abstract_canon_sha256":"d3cd9c593a42a9e657e83be4002f9b3fd6f7c644aa71e0c8f000abd00721f560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:49.904785Z","signature_b64":"o2P6INjmsU0+EciquNi1U71qDVCxCEpSVzZ8LuullP9TtZZhwho6JvXQ4N2f7yeZ4RnIjIHVTQA0I5vkAScgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","last_reissued_at":"2026-07-14T01:21:49.903940Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:49.903940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aashu Singh, Fei Liu, Hanchao Yu, Jianyu Wang, Jingcheng Yang, Jize Jiang, Khoi Pham, Klara Nahrstedt, Mingyuan Wu, Qifan Wang, Shengyi Qian, Xudong Wang, Zhaolun Su, Zhuokai Zhao","submitted_at":"2026-07-13T00:21:30Z","abstract_excerpt":"We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the model proposes an answer using the same weights, and issues a binary self-verdict (Yes/No). A 'No' triggers a second-chance rethink; a 'Yes,' or a turn cap, finalizes the output for computing the outcome-based reward. SVR-R1 is implemented with GRPO and an asynchronous multi-turn rollout framework and needs no external supervision or auxiliary critics. We evaluate SVR-R1 on vision-language reasoning benchmarks and sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10966","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/2607.10966/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":"2607.10966","created_at":"2026-07-14T01:21:49.904384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10966v1","created_at":"2026-07-14T01:21:49.904384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10966","created_at":"2026-07-14T01:21:49.904384+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLBDJIXQPOCU","created_at":"2026-07-14T01:21:49.904384+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLBDJIXQPOCUVKEW","created_at":"2026-07-14T01:21:49.904384+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLBDJIXQ","created_at":"2026-07-14T01:21:49.904384+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/NLBDJIXQPOCUVKEWMI6LGT6CGD","json":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD.json","graph_json":"https://pith.science/api/pith-number/NLBDJIXQPOCUVKEWMI6LGT6CGD/graph.json","events_json":"https://pith.science/api/pith-number/NLBDJIXQPOCUVKEWMI6LGT6CGD/events.json","paper":"https://pith.science/paper/NLBDJIXQ"},"agent_actions":{"view_html":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD","download_json":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD.json","view_paper":"https://pith.science/paper/NLBDJIXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10966&json=true","fetch_graph":"https://pith.science/api/pith-number/NLBDJIXQPOCUVKEWMI6LGT6CGD/graph.json","fetch_events":"https://pith.science/api/pith-number/NLBDJIXQPOCUVKEWMI6LGT6CGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/action/storage_attestation","attest_author":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/action/author_attestation","sign_citation":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/action/citation_signature","submit_replication":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/action/replication_record"}},"created_at":"2026-07-14T01:21:49.904384+00:00","updated_at":"2026-07-14T01:21:49.904384+00:00"}