{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EKTWO4O3IBM2OYXMPE3PHW26FP","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":"130a600f437012a3e006800b4500e0c1beca3cd44bcfbdce19e8a2e14ec1cdc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:07:25Z","title_canon_sha256":"7bd319f6f02bc15cbd8e355c53973ce798d41f91b114344b47bc90ac0b1fcc57"},"schema_version":"1.0","source":{"id":"2605.31096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31096","created_at":"2026-06-01T01:03:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31096v1","created_at":"2026-06-01T01:03:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31096","created_at":"2026-06-01T01:03:57Z"},{"alias_kind":"pith_short_12","alias_value":"EKTWO4O3IBM2","created_at":"2026-06-01T01:03:57Z"},{"alias_kind":"pith_short_16","alias_value":"EKTWO4O3IBM2OYXM","created_at":"2026-06-01T01:03:57Z"},{"alias_kind":"pith_short_8","alias_value":"EKTWO4O3","created_at":"2026-06-01T01:03:57Z"}],"graph_snapshots":[{"event_id":"sha256:75a7341dda941b0f9987b2f8dbf710948d90b5d2fc6cc3138d602baf6d2909b6","target":"graph","created_at":"2026-06-01T01:03:57Z","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/2605.31096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language models (MLLMs), its efficacy during the inference phase remains underexplored. In this work, we empirically find that mandating explicit object boxes in visually grounded CoT during inference often degrades performance compared to standard textual CoT, which reasons without explicit visual grounding. We hypothesize that the visual localization capability can be internalized into the textual CoT and that the mandatory explicit grounding introduces un","authors_text":"Chang-Bin Zhang, Kai Han, Qiang Zhang, Yujie Zhong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:07:25Z","title":"iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31096","kind":"arxiv","version":1},"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:aef2199c5b663fc3cba0a7ac8cfa209fb737ad19eaabc2294db76e2b2acf52e4","target":"record","created_at":"2026-06-01T01:03:57Z","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":"130a600f437012a3e006800b4500e0c1beca3cd44bcfbdce19e8a2e14ec1cdc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:07:25Z","title_canon_sha256":"7bd319f6f02bc15cbd8e355c53973ce798d41f91b114344b47bc90ac0b1fcc57"},"schema_version":"1.0","source":{"id":"2605.31096","kind":"arxiv","version":1}},"canonical_sha256":"22a76771db4059a762ec7936f3db5e2be4d58efbc8456e3dcf1d99a8e12b2ec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22a76771db4059a762ec7936f3db5e2be4d58efbc8456e3dcf1d99a8e12b2ec2","first_computed_at":"2026-06-01T01:03:57.714047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:57.714047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/dSGTpE2dgJB22HfGv+RI38I83x4xlN1PjjsN9QVTVNr08qNvGqQiF/zQigla6KJFgJqeNGnQNlzGy7TYLaSBQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:57.714686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aef2199c5b663fc3cba0a7ac8cfa209fb737ad19eaabc2294db76e2b2acf52e4","sha256:75a7341dda941b0f9987b2f8dbf710948d90b5d2fc6cc3138d602baf6d2909b6"],"state_sha256":"868153b1aa6e594c47c8c8ab89c4d99e50fcc95366cb43c17fc07151eddd0d53"}