{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6AVSL3D6IDIFXNW3WIRUZTW6E4","short_pith_number":"pith:6AVSL3D6","canonical_record":{"source":{"id":"2606.13156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T10:27:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9522d90b78b706860a9ff0e000ce52fa8773c1c863c7b526f50a01d7d8c3320f","abstract_canon_sha256":"967bec805f6e53ea2a7751ffc111102b3a1244a7b460cb6d640b71300629381c"},"schema_version":"1.0"},"canonical_sha256":"f02b25ec7e40d05bb6dbb2234ccede272e5562e60dcf2efd01f819370cac98d1","source":{"kind":"arxiv","id":"2606.13156","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6AVSL3D6IDIFXNW3WIRUZTW6E4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.13156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T10:27:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9522d90b78b706860a9ff0e000ce52fa8773c1c863c7b526f50a01d7d8c3320f","abstract_canon_sha256":"967bec805f6e53ea2a7751ffc111102b3a1244a7b460cb6d640b71300629381c"},"schema_version":"1.0"},"canonical_sha256":"f02b25ec7e40d05bb6dbb2234ccede272e5562e60dcf2efd01f819370cac98d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:43.895147Z","signature_b64":"ejUiKcYKeQCZFVBrlPiHeUe8fEMrSVJ0i1VAmpXr4UpiY8BpMMoA7Z+4u62w0I0j7irWQEKLDIx2iGbrXsyXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f02b25ec7e40d05bb6dbb2234ccede272e5562e60dcf2efd01f819370cac98d1","last_reissued_at":"2026-06-12T01:09:43.894178Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:43.894178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.13156","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iHuPf1R7e86R6xLXMTWYfE9Iy1x3evfG2yPTQ4kb4/Cix1LOE/Y5W6Uc4KJ/UyszlHuYtJfYAyIE5E/mKc8RCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T12:48:25.274020Z"},"content_sha256":"3cbd6d547aa8192300e776e5519c37ac26099add5f2fe5cc9f4b70f597f37224","schema_version":"1.0","event_id":"sha256:3cbd6d547aa8192300e776e5519c37ac26099add5f2fe5cc9f4b70f597f37224"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6AVSL3D6IDIFXNW3WIRUZTW6E4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Animesh Tripathy, Aswanth Krishnan","submitted_at":"2026-06-11T10:27:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13156","kind":"arxiv","version":1},"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/2606.13156/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUpJ6YLXuthWlSJ0eEzdq0xxV/0OpScHVCpSmuq4inuViM33b2QdZQp96OsVHcX3kHSiU3XW5X8j7pDIsWsgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T12:48:25.274411Z"},"content_sha256":"dd94a20b481c1a2b1b061c6572535aaa25da0d764f538eaf83f43db36de2b7ab","schema_version":"1.0","event_id":"sha256:dd94a20b481c1a2b1b061c6572535aaa25da0d764f538eaf83f43db36de2b7ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4/bundle.json","state_url":"https://pith.science/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T12:48:25Z","links":{"resolver":"https://pith.science/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4","bundle":"https://pith.science/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4/bundle.json","state":"https://pith.science/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6AVSL3D6IDIFXNW3WIRUZTW6E4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRPA9qAcd0RPNjb27miKKPa1I9HJZ5bFxWvPZtnNB0oFLXGZ7cY+/+XenjMd2xI6OSjKs5Lp94Ay9HcuRYTcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T12:48:25.276443Z","bundle_sha256":"b1dabc8ba5173eaaf06454dbd781d59650b9f166de07e17b7df251d64dada443"}}