{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HM3H4A2LIJGOLHBJYL3SCEYIEA","short_pith_number":"pith:HM3H4A2L","schema_version":"1.0","canonical_sha256":"3b367e034b424ce59c29c2f72113082015f74ba14d90affff1e6b64e6946f073","source":{"kind":"arxiv","id":"2606.28385","version":1},"attestation_state":"computed","paper":{"title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","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","submitted_at":"2026-06-22T06:45:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.28385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T06:45:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2021b840147153df09b212d3b7cba4c90ca58551e73dfaba1a03f86d53bbd5e8","abstract_canon_sha256":"d066db7ae09b35db8b2233180b5e816d294ddd2fd44c4a69988b87420c1f22a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:12.618927Z","signature_b64":"KXjvrfKdm97tAYXt7X9PLFh2JtnsaYEdZfzdN1UPOAyYR0zGDEaJDVRIyG7ZSxISqVLmV+/xyZDidg8419c2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b367e034b424ce59c29c2f72113082015f74ba14d90affff1e6b64e6946f073","last_reissued_at":"2026-06-30T00:15:12.618525Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:12.618525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","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","submitted_at":"2026-06-22T06:45:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28385","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/2606.28385/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.28385","created_at":"2026-06-30T00:15:12.618582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28385v1","created_at":"2026-06-30T00:15:12.618582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28385","created_at":"2026-06-30T00:15:12.618582+00:00"},{"alias_kind":"pith_short_12","alias_value":"HM3H4A2LIJGO","created_at":"2026-06-30T00:15:12.618582+00:00"},{"alias_kind":"pith_short_16","alias_value":"HM3H4A2LIJGOLHBJ","created_at":"2026-06-30T00:15:12.618582+00:00"},{"alias_kind":"pith_short_8","alias_value":"HM3H4A2L","created_at":"2026-06-30T00:15:12.618582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA","json":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA.json","graph_json":"https://pith.science/api/pith-number/HM3H4A2LIJGOLHBJYL3SCEYIEA/graph.json","events_json":"https://pith.science/api/pith-number/HM3H4A2LIJGOLHBJYL3SCEYIEA/events.json","paper":"https://pith.science/paper/HM3H4A2L"},"agent_actions":{"view_html":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA","download_json":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA.json","view_paper":"https://pith.science/paper/HM3H4A2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28385&json=true","fetch_graph":"https://pith.science/api/pith-number/HM3H4A2LIJGOLHBJYL3SCEYIEA/graph.json","fetch_events":"https://pith.science/api/pith-number/HM3H4A2LIJGOLHBJYL3SCEYIEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA/action/storage_attestation","attest_author":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA/action/author_attestation","sign_citation":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA/action/citation_signature","submit_replication":"https://pith.science/pith/HM3H4A2LIJGOLHBJYL3SCEYIEA/action/replication_record"}},"created_at":"2026-06-30T00:15:12.618582+00:00","updated_at":"2026-06-30T00:15:12.618582+00:00"}