{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HM3H4A2LIJGOLHBJYL3SCEYIEA","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":"d066db7ae09b35db8b2233180b5e816d294ddd2fd44c4a69988b87420c1f22a3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T06:45:09Z","title_canon_sha256":"2021b840147153df09b212d3b7cba4c90ca58551e73dfaba1a03f86d53bbd5e8"},"schema_version":"1.0","source":{"id":"2606.28385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28385","created_at":"2026-06-30T00:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28385v1","created_at":"2026-06-30T00:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28385","created_at":"2026-06-30T00:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"HM3H4A2LIJGO","created_at":"2026-06-30T00:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"HM3H4A2LIJGOLHBJ","created_at":"2026-06-30T00:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"HM3H4A2L","created_at":"2026-06-30T00:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:3c107032e0b8931c1d11bf756d6b2df5193d8f3126149fc92382deb2d7c6a886","target":"graph","created_at":"2026-06-30T00:15:12Z","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/2606.28385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in robot world models enable synthetic video generation for embodied prediction and planning. However, evaluating these videos is challenging: visually realistic outputs often violate physical laws, temporal consistency, or task logic, while conventional metrics and monolithic Vision-Language Model (VLM) judges fail to generalize or provide precise diagnostic value. We present RoboGaze, a training-free, multi-agent VLM framework that provides structured, interpretable evaluation for generated robot-manipulation videos. Given a task instruction and video, RoboGaze operates via a","authors_text":"An Thai Le, Daniel Sonntag, Doanh Le Thien, Dung D. Le, Duy Minh Ho Nguyen, Hoang H. Tran, Hung Khang Nguyen, Minh Le, Minh-Loi Nguyen, Nghiem Tuong Diep, Tran Van Nhiem, Vien Anh Ngo, Vu N. Duong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T06:45:09Z","title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28385","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:c5d3a71a8dad3739175db18dbfd72e7c6691032b038496abdd221dc60e7142cd","target":"record","created_at":"2026-06-30T00:15:12Z","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":"d066db7ae09b35db8b2233180b5e816d294ddd2fd44c4a69988b87420c1f22a3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T06:45:09Z","title_canon_sha256":"2021b840147153df09b212d3b7cba4c90ca58551e73dfaba1a03f86d53bbd5e8"},"schema_version":"1.0","source":{"id":"2606.28385","kind":"arxiv","version":1}},"canonical_sha256":"3b367e034b424ce59c29c2f72113082015f74ba14d90affff1e6b64e6946f073","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b367e034b424ce59c29c2f72113082015f74ba14d90affff1e6b64e6946f073","first_computed_at":"2026-06-30T00:15:12.618525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:12.618525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXjvrfKdm97tAYXt7X9PLFh2JtnsaYEdZfzdN1UPOAyYR0zGDEaJDVRIyG7ZSxISqVLmV+/xyZDidg8419c2AQ==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:12.618927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5d3a71a8dad3739175db18dbfd72e7c6691032b038496abdd221dc60e7142cd","sha256:3c107032e0b8931c1d11bf756d6b2df5193d8f3126149fc92382deb2d7c6a886"],"state_sha256":"61ff0d6041b24670d0b5c8363bf5474f50cfd347ba96d51c9b85f8d8354e78be"}