{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IQSLBJORI73XLDVBQI7HEJNWI7","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":"6558e09569e342456df1fc25a0960a1a66c872f69211a2c740cebd7fec036f63","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T07:41:39Z","title_canon_sha256":"88a0d026f6ce7a94ea1a8703ee1ca815bb7c30ed627a34cebf4b2b10fcdb34ef"},"schema_version":"1.0","source":{"id":"2505.19017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19017","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19017v1","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19017","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"IQSLBJORI73X","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"IQSLBJORI73XLDVB","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"IQSLBJOR","created_at":"2026-07-05T11:09:23Z"}],"graph_snapshots":[{"event_id":"sha256:590ef2adc87e7d545598b0478e4df3685c41a5e9fa6cb392b1b9d5e800272c0a","target":"graph","created_at":"2026-07-05T11:09:23Z","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/2505.19017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of robotics has made significant strides toward developing generalist robot manipulation policies. However, evaluating these policies in real-world scenarios remains time-consuming and challenging, particularly as the number of tasks scales and environmental conditions change. In this work, we demonstrate that world models can serve as a scalable, reproducible, and reliable proxy for real-world robot policy evaluation. A key challenge is generating accurate policy videos from world models that faithfully reflect the robot actions. We observe that directly inputting robot actions or u","authors_text":"Chaomin Shen, Junjie Wen, Yaxuan Li, Yichen Zhu, Yi Xu","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T07:41:39Z","title":"WorldEval: World Model as Real-World Robot Policies Evaluator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19017","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":"sha256:6c07f03bf537808f67b77bec7a1f6dbb1669f6339015193622b3dc3367f07a39","target":"record","created_at":"2026-07-05T11:09:23Z","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":"6558e09569e342456df1fc25a0960a1a66c872f69211a2c740cebd7fec036f63","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T07:41:39Z","title_canon_sha256":"88a0d026f6ce7a94ea1a8703ee1ca815bb7c30ed627a34cebf4b2b10fcdb34ef"},"schema_version":"1.0","source":{"id":"2505.19017","kind":"arxiv","version":1}},"canonical_sha256":"4424b0a5d147f7758ea1823e7225b647d7427d3fdc0c68272782809b2ae655d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4424b0a5d147f7758ea1823e7225b647d7427d3fdc0c68272782809b2ae655d5","first_computed_at":"2026-07-05T11:09:23.569239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:23.569239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uI94+tRhO57pMIoafuIOk+DCdDAN52jOWMyG8Ao5nFeXZJzmcxsGFDIkGM7qyoxoTtR/IdAgHjKgSAnEr1/4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:23.569774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c07f03bf537808f67b77bec7a1f6dbb1669f6339015193622b3dc3367f07a39","sha256:590ef2adc87e7d545598b0478e4df3685c41a5e9fa6cb392b1b9d5e800272c0a"],"state_sha256":"58784f4ba9e9f203d9b7287ce193691cb8adb5dd01b363c38936611b3d829aed"}