{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6AVSL3D6IDIFXNW3WIRUZTW6E4","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":"967bec805f6e53ea2a7751ffc111102b3a1244a7b460cb6d640b71300629381c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T10:27:29Z","title_canon_sha256":"9522d90b78b706860a9ff0e000ce52fa8773c1c863c7b526f50a01d7d8c3320f"},"schema_version":"1.0","source":{"id":"2606.13156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13156","created_at":"2026-06-12T01:09:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13156v1","created_at":"2026-06-12T01:09:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13156","created_at":"2026-06-12T01:09:43Z"},{"alias_kind":"pith_short_12","alias_value":"6AVSL3D6IDIF","created_at":"2026-06-12T01:09:43Z"},{"alias_kind":"pith_short_16","alias_value":"6AVSL3D6IDIFXNW3","created_at":"2026-06-12T01:09:43Z"},{"alias_kind":"pith_short_8","alias_value":"6AVSL3D6","created_at":"2026-06-12T01:09:43Z"}],"graph_snapshots":[{"event_id":"sha256:dd94a20b481c1a2b1b061c6572535aaa25da0d764f538eaf83f43db36de2b7ab","target":"graph","created_at":"2026-06-12T01:09:43Z","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/2606.13156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) achieve strong singleshot spatial grounding, yet lack any mechanism to observe and correct their own predictions. We find that naively prompting a VLM to iterate over rendered visualizations of its predictions causes catastrophic failure: Acc@0.5 on referring expression comprehension collapses from 79.6% to 48.7% (a 31 percentage point drop), revealing a fundamental gap between grounding capability and self-correction ability. We propose Iterative Visual Thinking (IVT), a closed-loop framework in which the model predicts a bounding box, observes the prediction ren","authors_text":"Animesh Tripathy, Aswanth Krishnan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T10:27:29Z","title":"Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13156","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":"sha256:3cbd6d547aa8192300e776e5519c37ac26099add5f2fe5cc9f4b70f597f37224","target":"record","created_at":"2026-06-12T01:09:43Z","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":"967bec805f6e53ea2a7751ffc111102b3a1244a7b460cb6d640b71300629381c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T10:27:29Z","title_canon_sha256":"9522d90b78b706860a9ff0e000ce52fa8773c1c863c7b526f50a01d7d8c3320f"},"schema_version":"1.0","source":{"id":"2606.13156","kind":"arxiv","version":1}},"canonical_sha256":"f02b25ec7e40d05bb6dbb2234ccede272e5562e60dcf2efd01f819370cac98d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f02b25ec7e40d05bb6dbb2234ccede272e5562e60dcf2efd01f819370cac98d1","first_computed_at":"2026-06-12T01:09:43.894178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:43.894178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ejUiKcYKeQCZFVBrlPiHeUe8fEMrSVJ0i1VAmpXr4UpiY8BpMMoA7Z+4u62w0I0j7irWQEKLDIx2iGbrXsyXDw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:43.895147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cbd6d547aa8192300e776e5519c37ac26099add5f2fe5cc9f4b70f597f37224","sha256:dd94a20b481c1a2b1b061c6572535aaa25da0d764f538eaf83f43db36de2b7ab"],"state_sha256":"5bb50ce15356116131156f784300e01cc8afdadceb17956759ca9783244b7820"}