{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VWW4R72IW6ZN7WCSLQV5BTJFF6","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":"6498fb99823997d8e0e27510875baf8fde71f185dda8800682f636e67866aa09","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T08:15:23Z","title_canon_sha256":"ab9f0c1e572d573a9330d99f11785df38ab84434f571eb0190c0b7710b32cb7a"},"schema_version":"1.0","source":{"id":"2605.29563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29563","created_at":"2026-05-29T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29563v1","created_at":"2026-05-29T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29563","created_at":"2026-05-29T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"VWW4R72IW6ZN","created_at":"2026-05-29T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"VWW4R72IW6ZN7WCS","created_at":"2026-05-29T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"VWW4R72I","created_at":"2026-05-29T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:575125a5b5a6ed98061d9dc7a4a0abe3b3842256bbe32bafd69dafbbf1c67b73","target":"graph","created_at":"2026-05-29T01:05:47Z","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/2605.29563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transforms the view, and (2)composing many such transformations across multi-turn plans to identify a target view. We probe both abilities in our proposed ViewSuite, a 3D point-cloud environment on real ScanNet scenes. Across 13 frontier VLMs, a critical planning gap emerges: they possess basic view-action knowledge but fail to compose it across multi-turn plans, with the gap widening as viewpoint distance grows. To close ","authors_text":"Jiajun Wu, Kangrui Wang, Leonidas Guibas, Li Fei-Fei, Lijuan Wang, Linjie Li, Manling Li, Shiqi Chen, Zhengyuan Yang, Zihan Wang","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T08:15:23Z","title":"Planning with the Views via Scene Self-Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29563","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":"sha256:2af987670308ec833553588d94231f2ae0cbbc3fae3950c112b588fa01eaa918","target":"record","created_at":"2026-05-29T01:05:47Z","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":"6498fb99823997d8e0e27510875baf8fde71f185dda8800682f636e67866aa09","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T08:15:23Z","title_canon_sha256":"ab9f0c1e572d573a9330d99f11785df38ab84434f571eb0190c0b7710b32cb7a"},"schema_version":"1.0","source":{"id":"2605.29563","kind":"arxiv","version":1}},"canonical_sha256":"adadc8ff48b7b2dfd8525c2bd0cd252fb8d8c55d1f36e8ab46db4039e692185c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adadc8ff48b7b2dfd8525c2bd0cd252fb8d8c55d1f36e8ab46db4039e692185c","first_computed_at":"2026-05-29T01:05:47.608884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:47.608884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/jS/ICB2p063PXYO8mY6b2YZXVNRSbuyiBNuG0UJ1S3dh8XwXnbpgnyuBoPr01XD6inOezfj9tA3Px/z+WZLAw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:47.609680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2af987670308ec833553588d94231f2ae0cbbc3fae3950c112b588fa01eaa918","sha256:575125a5b5a6ed98061d9dc7a4a0abe3b3842256bbe32bafd69dafbbf1c67b73"],"state_sha256":"a66ce80f5ae2465d198a0955c38a00e07360cc1cf7d3558d3ec2bfd84f1ffa3f"}