{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RK65EMHD6XRKNHENK2NOX2TR2W","short_pith_number":"pith:RK65EMHD","schema_version":"1.0","canonical_sha256":"8abdd230e3f5e2a69c8d569aebea71d5a1c6b9c2bbe2586b5167926d28347867","source":{"kind":"arxiv","id":"2505.16192","version":2},"attestation_state":"computed","paper":{"title":"VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Han Yang, Ji Zhang, Ming Yan, Shikun Zhang, Wei Ye, Yongrui Heng","submitted_at":"2025-05-22T03:50:13Z","abstract_excerpt":"Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual regions to achieve precise grounding of textual reasoning in visual evidence. We introduce \\textbf{VLM-R$^3$} (\\textbf{V}isual \\textbf{L}anguage \\textbf{M}odel with \\textbf{R}egion \\textbf{R}ecognition and \\textbf{R}easoning), a framework that equips an MLLM with the ability to (i) decide \\emph{when} additional visual evidence is needed, (ii) determine \\emph"},"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":"2505.16192","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T03:50:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93f35dd3a415589f4f2433ec53865e7837195f1a5b50850d0daefb585a637fe9","abstract_canon_sha256":"9ed53f7a30de6845f4ab34a6197fbccd8038b300a2fe3f5048a1fe798085287b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:32.570124Z","signature_b64":"lIjoCYr+MHqFc/zgKux5fWSu4OEcfNNNI+A0SHrgKQr5yo+VuO5j5d2Akl95iHHT15w/029KY2o18KW3d7xACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8abdd230e3f5e2a69c8d569aebea71d5a1c6b9c2bbe2586b5167926d28347867","last_reissued_at":"2026-07-05T11:12:32.569598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:32.569598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Han Yang, Ji Zhang, Ming Yan, Shikun Zhang, Wei Ye, Yongrui Heng","submitted_at":"2025-05-22T03:50:13Z","abstract_excerpt":"Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual regions to achieve precise grounding of textual reasoning in visual evidence. We introduce \\textbf{VLM-R$^3$} (\\textbf{V}isual \\textbf{L}anguage \\textbf{M}odel with \\textbf{R}egion \\textbf{R}ecognition and \\textbf{R}easoning), a framework that equips an MLLM with the ability to (i) decide \\emph{when} additional visual evidence is needed, (ii) determine \\emph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16192","kind":"arxiv","version":2},"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/2505.16192/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":"2505.16192","created_at":"2026-07-05T11:12:32.569663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16192v2","created_at":"2026-07-05T11:12:32.569663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16192","created_at":"2026-07-05T11:12:32.569663+00:00"},{"alias_kind":"pith_short_12","alias_value":"RK65EMHD6XRK","created_at":"2026-07-05T11:12:32.569663+00:00"},{"alias_kind":"pith_short_16","alias_value":"RK65EMHD6XRKNHEN","created_at":"2026-07-05T11:12:32.569663+00:00"},{"alias_kind":"pith_short_8","alias_value":"RK65EMHD","created_at":"2026-07-05T11:12:32.569663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26631","citing_title":"Position Rebinding Cache Reuse: Replay-Free Visual Revisiting for Interleaved Multimodal Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29672","citing_title":"How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29672","citing_title":"How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01843","citing_title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14044","citing_title":"OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05271","citing_title":"DeepEyesV2: Toward Agentic Multimodal Model","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12163","citing_title":"Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02794","citing_title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12163","citing_title":"Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05045","citing_title":"When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03485","citing_title":"MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24339","citing_title":"See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05045","citing_title":"When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02730","citing_title":"Perceptual Flow Network for Visually Grounded Reasoning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W","json":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W.json","graph_json":"https://pith.science/api/pith-number/RK65EMHD6XRKNHENK2NOX2TR2W/graph.json","events_json":"https://pith.science/api/pith-number/RK65EMHD6XRKNHENK2NOX2TR2W/events.json","paper":"https://pith.science/paper/RK65EMHD"},"agent_actions":{"view_html":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W","download_json":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W.json","view_paper":"https://pith.science/paper/RK65EMHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16192&json=true","fetch_graph":"https://pith.science/api/pith-number/RK65EMHD6XRKNHENK2NOX2TR2W/graph.json","fetch_events":"https://pith.science/api/pith-number/RK65EMHD6XRKNHENK2NOX2TR2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W/action/storage_attestation","attest_author":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W/action/author_attestation","sign_citation":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W/action/citation_signature","submit_replication":"https://pith.science/pith/RK65EMHD6XRKNHENK2NOX2TR2W/action/replication_record"}},"created_at":"2026-07-05T11:12:32.569663+00:00","updated_at":"2026-07-05T11:12:32.569663+00:00"}