{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:34CK2UTV2VAGPYHOJF2VPPLPMN","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":"16c5d61b64a44cf76be922cfc5099abc9cd863333b36386a5111b93de1d005f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T19:51:54Z","title_canon_sha256":"cd6aca0d7b302bd19fad9cfc332720f596c020101590ca3d519993df81bfae04"},"schema_version":"1.0","source":{"id":"2607.00115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00115","created_at":"2026-07-02T00:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00115v1","created_at":"2026-07-02T00:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00115","created_at":"2026-07-02T00:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"34CK2UTV2VAG","created_at":"2026-07-02T00:18:35Z"},{"alias_kind":"pith_short_16","alias_value":"34CK2UTV2VAGPYHO","created_at":"2026-07-02T00:18:35Z"},{"alias_kind":"pith_short_8","alias_value":"34CK2UTV","created_at":"2026-07-02T00:18:35Z"}],"graph_snapshots":[{"event_id":"sha256:350d4ab78a70fc4e7d6012804be83bf0e0df8e20d125ac14a5b7e3810cdb79c2","target":"graph","created_at":"2026-07-02T00:18:35Z","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/2607.00115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure to the entanglement of reasoning and perception within a single model, the MLLM reasons and localizes simultaneously, and inaccurate localization triggers additional reasoning turns that bloat the trajectory. To solve this problem, we propose PixelEyes, a multi-turn visual reasoning agent that explicitly decouples reasoning from perception, i.e., the reasoner decides what to look for, while a specialized perception to","authors_text":"Dengxian Gong, Haobo Yuan, Haochen Wang, Jason Li, Kai Wang, Lu Qi, Ming-Hsuan Yang, Quanzhu Niu, Shihao Chen, Shunping Ji, Tao Zhang, Yikang Zhou, Yuanzheng Wu, Zhengdong Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T19:51:54Z","title":"PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00115","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":"sha256:3a8b9d14d9eef618c77fd24e01de2253506a21fd27e0aaa4a03c92c427784879","target":"record","created_at":"2026-07-02T00:18:35Z","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":"16c5d61b64a44cf76be922cfc5099abc9cd863333b36386a5111b93de1d005f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T19:51:54Z","title_canon_sha256":"cd6aca0d7b302bd19fad9cfc332720f596c020101590ca3d519993df81bfae04"},"schema_version":"1.0","source":{"id":"2607.00115","kind":"arxiv","version":1}},"canonical_sha256":"df04ad5275d54067e0ee497557bd6f636b5f69065e89ff1156f34c01e74098f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df04ad5275d54067e0ee497557bd6f636b5f69065e89ff1156f34c01e74098f2","first_computed_at":"2026-07-02T00:18:35.305942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:35.305942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XXoA6HqEnBs3SxUfG1LupDbCP79q3PuNu2ITD21EApGjM69vBDJV4PY1zgM7PLiiL3zN9M/KHEjAliZeBeB1CA==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:35.306418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a8b9d14d9eef618c77fd24e01de2253506a21fd27e0aaa4a03c92c427784879","sha256:350d4ab78a70fc4e7d6012804be83bf0e0df8e20d125ac14a5b7e3810cdb79c2"],"state_sha256":"f6a2b91e76477d2047a5a46956827b78f039af0f6fbe8bdf971c7654ebe0a6b0"}