{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RK65EMHD6XRKNHENK2NOX2TR2W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9ed53f7a30de6845f4ab34a6197fbccd8038b300a2fe3f5048a1fe798085287b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T03:50:13Z","title_canon_sha256":"93f35dd3a415589f4f2433ec53865e7837195f1a5b50850d0daefb585a637fe9"},"schema_version":"1.0","source":{"id":"2505.16192","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16192","created_at":"2026-07-05T11:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16192v2","created_at":"2026-07-05T11:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16192","created_at":"2026-07-05T11:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"RK65EMHD6XRK","created_at":"2026-07-05T11:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"RK65EMHD6XRKNHEN","created_at":"2026-07-05T11:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"RK65EMHD","created_at":"2026-07-05T11:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:92938df44f8eb6435c5b381559bcfa4e6c64259c64461325669c507da2f8c259","target":"graph","created_at":"2026-07-05T11:12:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Han Yang, Ji Zhang, Ming Yan, Shikun Zhang, Wei Ye, Yongrui Heng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T03:50:13Z","title":"VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16192","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3b107bdfec5e61f9906a2327229f148f5943f5f2f58ce94e781f2e63b28bf625","target":"record","created_at":"2026-07-05T11:12:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9ed53f7a30de6845f4ab34a6197fbccd8038b300a2fe3f5048a1fe798085287b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T03:50:13Z","title_canon_sha256":"93f35dd3a415589f4f2433ec53865e7837195f1a5b50850d0daefb585a637fe9"},"schema_version":"1.0","source":{"id":"2505.16192","kind":"arxiv","version":2}},"canonical_sha256":"8abdd230e3f5e2a69c8d569aebea71d5a1c6b9c2bbe2586b5167926d28347867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8abdd230e3f5e2a69c8d569aebea71d5a1c6b9c2bbe2586b5167926d28347867","first_computed_at":"2026-07-05T11:12:32.569598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:32.569598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lIjoCYr+MHqFc/zgKux5fWSu4OEcfNNNI+A0SHrgKQr5yo+VuO5j5d2Akl95iHHT15w/029KY2o18KW3d7xACg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:32.570124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16192","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b107bdfec5e61f9906a2327229f148f5943f5f2f58ce94e781f2e63b28bf625","sha256:92938df44f8eb6435c5b381559bcfa4e6c64259c64461325669c507da2f8c259"],"state_sha256":"eaf936908e812fef93f67853320ab65dc8a669f11788d8a77459fcd0a9fed968"}