{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DDVCFKBV6TI5OAT3FO6436NNVS","short_pith_number":"pith:DDVCFKBV","schema_version":"1.0","canonical_sha256":"18ea22a835f4d1d7027b2bbdcdf9adac973cdd8d4d94e4f68b1b9499db632566","source":{"kind":"arxiv","id":"2503.17352","version":3},"attestation_state":"computed","paper":{"title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fan Yin, Hritik Bansal, Kai-Wei Chang, Nanyun Peng, Wei Wang, Yihe Deng","submitted_at":"2025-03-21T17:52:43Z","abstract_excerpt":"We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gains on challenging visual reasoning tasks. While text-based reasoning models (e.g., Deepseek R1) show promising results in text-only tasks, distilling their reasoning into LVLMs via supervised fine-tuning (SFT) often results in performance degradation due to imprecise visual grounding. Conversely, purely reinforcement learning (RL)-based methods face a large search space, hindering the emergence of reflective behavior"},"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":"2503.17352","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T17:52:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e11cb380f9971b5a97a0ece6d33a06056bc3a8f7b9c7f10eb0feeeb1eb56cf0c","abstract_canon_sha256":"8078c42ef44f72a90c6a5e37b70ad335b42d323815111bbb5a3ae96e8977b0d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T06:53:51.355164Z","signature_b64":"GlsM7+2t6GKtO/+TSu8u8tFqxkAd1ufdIbG/XG2EwkKiaeuoaPWfReDWQUqhlq7k4yzA7Bl0LKnEVLbfnWFOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18ea22a835f4d1d7027b2bbdcdf9adac973cdd8d4d94e4f68b1b9499db632566","last_reissued_at":"2026-05-19T06:53:51.353252Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T06:53:51.353252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fan Yin, Hritik Bansal, Kai-Wei Chang, Nanyun Peng, Wei Wang, Yihe Deng","submitted_at":"2025-03-21T17:52:43Z","abstract_excerpt":"We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gains on challenging visual reasoning tasks. While text-based reasoning models (e.g., Deepseek R1) show promising results in text-only tasks, distilling their reasoning into LVLMs via supervised fine-tuning (SFT) often results in performance degradation due to imprecise visual grounding. Conversely, purely reinforcement learning (RL)-based methods face a large search space, hindering the emergence of reflective behavior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17352","kind":"arxiv","version":3},"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/2503.17352/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":"2503.17352","created_at":"2026-05-19T06:53:51.353350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17352v3","created_at":"2026-05-19T06:53:51.353350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17352","created_at":"2026-05-19T06:53:51.353350+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDVCFKBV6TI5","created_at":"2026-05-19T06:53:51.353350+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDVCFKBV6TI5OAT3","created_at":"2026-05-19T06:53:51.353350+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDVCFKBV","created_at":"2026-05-19T06:53:51.353350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2506.16796","citing_title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00748","citing_title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2508.11196","citing_title":"UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2509.23322","citing_title":"Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2510.21122","citing_title":"NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2505.21374","citing_title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2506.09965","citing_title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2504.06958","citing_title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12004","citing_title":"Learning Agentic Policy from Action Guidance","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09262","citing_title":"Reinforcing Multimodal Reasoning Against Visual Degradation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10761","citing_title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22498","citing_title":"CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06121","citing_title":"Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21268","citing_title":"Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20486","citing_title":"ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19264","citing_title":"DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10219","citing_title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01882","citing_title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04379","citing_title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21409","citing_title":"S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS","json":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS.json","graph_json":"https://pith.science/api/pith-number/DDVCFKBV6TI5OAT3FO6436NNVS/graph.json","events_json":"https://pith.science/api/pith-number/DDVCFKBV6TI5OAT3FO6436NNVS/events.json","paper":"https://pith.science/paper/DDVCFKBV"},"agent_actions":{"view_html":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS","download_json":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS.json","view_paper":"https://pith.science/paper/DDVCFKBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17352&json=true","fetch_graph":"https://pith.science/api/pith-number/DDVCFKBV6TI5OAT3FO6436NNVS/graph.json","fetch_events":"https://pith.science/api/pith-number/DDVCFKBV6TI5OAT3FO6436NNVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS/action/storage_attestation","attest_author":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS/action/author_attestation","sign_citation":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS/action/citation_signature","submit_replication":"https://pith.science/pith/DDVCFKBV6TI5OAT3FO6436NNVS/action/replication_record"}},"created_at":"2026-05-19T06:53:51.353350+00:00","updated_at":"2026-05-19T06:53:51.353350+00:00"}