{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TXJR54DUZMEVE4AZH2Q5WVU6IU","short_pith_number":"pith:TXJR54DU","canonical_record":{"source":{"id":"2602.06508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","cross_cats_sorted":[],"title_canon_sha256":"15b9f478587eada233616d273554b93b613d0cb6d6dc6a71d55a9566c65bf097","abstract_canon_sha256":"435fc8d99593b354349fae080aed462e4d1c4e3df96863e2e1e0bd819b9e0bde"},"schema_version":"1.0"},"canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","source":{"kind":"arxiv","id":"2602.06508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06508","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06508v2","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06508","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"TXJR54DUZMEV","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"TXJR54DUZMEVE4AZ","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"TXJR54DU","created_at":"2026-05-26T02:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TXJR54DUZMEVE4AZH2Q5WVU6IU","target":"record","payload":{"canonical_record":{"source":{"id":"2602.06508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","cross_cats_sorted":[],"title_canon_sha256":"15b9f478587eada233616d273554b93b613d0cb6d6dc6a71d55a9566c65bf097","abstract_canon_sha256":"435fc8d99593b354349fae080aed462e4d1c4e3df96863e2e1e0bd819b9e0bde"},"schema_version":"1.0"},"canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:05.196997Z","signature_b64":"GzRve1GWzckqbZHdyID2M9lSyx3bzDGVe+tRLrrgKeRPfr8G9kikAy1VBmf+7v8iaj7/Vr02O7nrBL/DZJVtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","last_reissued_at":"2026-05-26T02:04:05.196105Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:05.196105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.06508","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPtfsbTd+FlRnjkk7Wy/rBxRE+jo9ade1m5ljtwmhxgPfNsbxZ0F94flTQtLsFl8Y70q6d28+SVzxVPPtxkLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:31:37.239161Z"},"content_sha256":"3e3b3b90fbb28c461c5a7312cd2d09376eab7cf5b074fdbd8e587405970fcc29","schema_version":"1.0","event_id":"sha256:3e3b3b90fbb28c461c5a7312cd2d09376eab7cf5b074fdbd8e587405970fcc29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TXJR54DUZMEVE4AZH2Q5WVU6IU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hai Ci, Kevin Yuchen Ma, Mike Zheng Shou, Xiaokang Liu, Zechen Bai","submitted_at":"2026-02-06T08:57:55Z","abstract_excerpt":"Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world models offer an option to train in virtual environments, yet they exhibit imprecise action following, particularly on subtle near-success failures. Besides, they lack native reward signals for RL. Computing rewards based on inaccurate visual predictions remain unreliable. We introduce World-VLA-Loop, structured around two foundational designs and a higher-level c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06508","kind":"arxiv","version":2},"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/2602.06508/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mvd7bM56gFB0X3oNDTBXUF98b7RwkPLcYNqoLP95OU27ymiBvJeYsyXZuT50DrqrBwtUytaVspEkr+7ev1a4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:31:37.239834Z"},"content_sha256":"724585e87067ac944b2f69266ce82ab95cc1670268c9fa3fe3109d6607ae98e7","schema_version":"1.0","event_id":"sha256:724585e87067ac944b2f69266ce82ab95cc1670268c9fa3fe3109d6607ae98e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU/bundle.json","state_url":"https://pith.science/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T15:31:37Z","links":{"resolver":"https://pith.science/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU","bundle":"https://pith.science/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU/bundle.json","state":"https://pith.science/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXJR54DUZMEVE4AZH2Q5WVU6IU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXJR54DUZMEVE4AZH2Q5WVU6IU","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":"435fc8d99593b354349fae080aed462e4d1c4e3df96863e2e1e0bd819b9e0bde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","title_canon_sha256":"15b9f478587eada233616d273554b93b613d0cb6d6dc6a71d55a9566c65bf097"},"schema_version":"1.0","source":{"id":"2602.06508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06508","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06508v2","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06508","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"TXJR54DUZMEV","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"TXJR54DUZMEVE4AZ","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"TXJR54DU","created_at":"2026-05-26T02:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:724585e87067ac944b2f69266ce82ab95cc1670268c9fa3fe3109d6607ae98e7","target":"graph","created_at":"2026-05-26T02:04:05Z","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/2602.06508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world models offer an option to train in virtual environments, yet they exhibit imprecise action following, particularly on subtle near-success failures. Besides, they lack native reward signals for RL. Computing rewards based on inaccurate visual predictions remain unreliable. We introduce World-VLA-Loop, structured around two foundational designs and a higher-level c","authors_text":"Hai Ci, Kevin Yuchen Ma, Mike Zheng Shou, Xiaokang Liu, Zechen Bai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","title":"World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06508","kind":"arxiv","version":2},"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":"sha256:3e3b3b90fbb28c461c5a7312cd2d09376eab7cf5b074fdbd8e587405970fcc29","target":"record","created_at":"2026-05-26T02:04:05Z","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":"435fc8d99593b354349fae080aed462e4d1c4e3df96863e2e1e0bd819b9e0bde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","title_canon_sha256":"15b9f478587eada233616d273554b93b613d0cb6d6dc6a71d55a9566c65bf097"},"schema_version":"1.0","source":{"id":"2602.06508","kind":"arxiv","version":2}},"canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","first_computed_at":"2026-05-26T02:04:05.196105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:05.196105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzRve1GWzckqbZHdyID2M9lSyx3bzDGVe+tRLrrgKeRPfr8G9kikAy1VBmf+7v8iaj7/Vr02O7nrBL/DZJVtBg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:05.196997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e3b3b90fbb28c461c5a7312cd2d09376eab7cf5b074fdbd8e587405970fcc29","sha256:724585e87067ac944b2f69266ce82ab95cc1670268c9fa3fe3109d6607ae98e7"],"state_sha256":"4e9d0ac3e94e456c477ee48a6cdb5841957bf48a4c6d9fde6d87d9b1564d8daf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsVjyAqcDPi7mXrN+Gie0Xg4i5xbVV8n3aWr4DSxJgV1kfU8BJz5KfN/QWSLhur6tbU82HRFLzIgWXfBn8/nDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:31:37.243224Z","bundle_sha256":"9bcd4b0bf4298d59cbba43a45eae9e96a529f7fad3658c3302b89627ac465063"}}