{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EELNZ3PBX4THLYKMRTFP6CKB7P","short_pith_number":"pith:EELNZ3PB","canonical_record":{"source":{"id":"2604.27792","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-30T12:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"7d205ae59269763e4f1b882f0148b14e9c62b2bd1f57cab10915967e66289c9f","abstract_canon_sha256":"200189d0cb513e7d42493758cbcbb6429ed8904e1bc7fa52893e2680d5a79778"},"schema_version":"1.0"},"canonical_sha256":"2116dcede1bf2675e14c8ccaff0941fbd69e5eef6a0a7d1b1d392a13e81f7509","source":{"kind":"arxiv","id":"2604.27792","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27792","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27792v3","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27792","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"EELNZ3PBX4TH","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"EELNZ3PBX4THLYKM","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"EELNZ3PB","created_at":"2026-07-14T01:22:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EELNZ3PBX4THLYKMRTFP6CKB7P","target":"record","payload":{"canonical_record":{"source":{"id":"2604.27792","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-30T12:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"7d205ae59269763e4f1b882f0148b14e9c62b2bd1f57cab10915967e66289c9f","abstract_canon_sha256":"200189d0cb513e7d42493758cbcbb6429ed8904e1bc7fa52893e2680d5a79778"},"schema_version":"1.0"},"canonical_sha256":"2116dcede1bf2675e14c8ccaff0941fbd69e5eef6a0a7d1b1d392a13e81f7509","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:07.618677Z","signature_b64":"3f1Qqi/Rqd9lf0GMyDYsa3iSNYiZnPXNoJLIp42UqqZYJlRsneKl7XomGsD7GSEZGyi6PwzDADAtVqvP1uSqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2116dcede1bf2675e14c8ccaff0941fbd69e5eef6a0a7d1b1d392a13e81f7509","last_reissued_at":"2026-07-14T01:22:07.617794Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:07.617794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.27792","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0RIzGiv0XlhDHX2HKJuelEVvi/kzjKYpjPGq+PhHJXUvieUzwUvPCPNYD7tC+GXTF49h2JQubTT0E3nZv6jBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:27:31.974081Z"},"content_sha256":"e0fe0df2bb33d845594f77ebebe5ac93919b9284f41ad00a7efcbf2c2a4a17ad","schema_version":"1.0","event_id":"sha256:e0fe0df2bb33d845594f77ebebe5ac93919b9284f41ad00a7efcbf2c2a4a17ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EELNZ3PBX4THLYKMRTFP6CKB7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MotuBrain: An Advanced World Action Model for Robot Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single unified model achieves 95.8 percent success on complex robot tasks while adapting quickly to new embodiments.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chendong Xiang, Fan Bao, Haitian Liu, Hengkai Tan, Hongzhe Bi, James Li, Jiabao Liu, Jingrui Pang, Jun Zhu, Kiro Jing, Louis Liu, Mengchen Cai, MotuBrain Team, Rongxu Cui, Runqing Wang, Ruowen Zhao, Shuhe Huang, Yao Feng, Yinze Rong, Zeyuan Wang","submitted_at":"2026-04-30T12:34:44Z","abstract_excerpt":"Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, MotuBrain further introduces unified mu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the three-stream Mixture-of-Transformers architecture under a UniDiffuser formulation, combined with the listed training data mixtures and post-training optimizations, produces the reported performance gains without hidden overfitting or benchmark-specific tuning that would not transfer to other robot platforms or tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MotuBrain jointly models video and action via a three-stream Mixture-of-Transformers UniDiffuser to reach 95.8-96.1% success on RoboTwin 2.0 benchmarks, top EWMScore, and fast 11 Hz inference while adapting to new robots with 50-100 trajectories.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single unified model achieves 95.8 percent success on complex robot tasks while adapting quickly to new embodiments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3f44e7d87951c5efdbf100c97adccba2f3ba13db32103eeadffcb27b5a5a0a5b"},"source":{"id":"2604.27792","kind":"arxiv","version":3},"verdict":{"id":"58f4547f-2efa-4a66-959b-7d652ba30f17","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T05:39:13.885899Z","strongest_claim":"MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.","one_line_summary":"MotuBrain jointly models video and action via a three-stream Mixture-of-Transformers UniDiffuser to reach 95.8-96.1% success on RoboTwin 2.0 benchmarks, top EWMScore, and fast 11 Hz inference while adapting to new robots with 50-100 trajectories.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the three-stream Mixture-of-Transformers architecture under a UniDiffuser formulation, combined with the listed training data mixtures and post-training optimizations, produces the reported performance gains without hidden overfitting or benchmark-specific tuning that would not transfer to other robot platforms or tasks.","pith_extraction_headline":"A single unified model achieves 95.8 percent success on complex robot tasks while adapting quickly to new embodiments."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27792/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T21:38:48.784012Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:53:43.788826Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4087c4153b19a11457773160dc254d04e56c4576658394b282388d580fcacaa3"},"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":"58f4547f-2efa-4a66-959b-7d652ba30f17"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9UZUhpx7TDO9JHs9jBhRw/6LmLUCAvo4zG+e6pCy1kmfKjtCh1vwSG3GAoRAqKcSRzoYOs3BrK3wSk9UALYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:27:31.975252Z"},"content_sha256":"3e2f0a68396634eed2e6c122166d117e8cf62dbb0c37cdbf3a91a45966ab776e","schema_version":"1.0","event_id":"sha256:3e2f0a68396634eed2e6c122166d117e8cf62dbb0c37cdbf3a91a45966ab776e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EELNZ3PBX4THLYKMRTFP6CKB7P/bundle.json","state_url":"https://pith.science/pith/EELNZ3PBX4THLYKMRTFP6CKB7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EELNZ3PBX4THLYKMRTFP6CKB7P/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":"2026-08-04T21:27:31Z","links":{"resolver":"https://pith.science/pith/EELNZ3PBX4THLYKMRTFP6CKB7P","bundle":"https://pith.science/pith/EELNZ3PBX4THLYKMRTFP6CKB7P/bundle.json","state":"https://pith.science/pith/EELNZ3PBX4THLYKMRTFP6CKB7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EELNZ3PBX4THLYKMRTFP6CKB7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EELNZ3PBX4THLYKMRTFP6CKB7P","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":"200189d0cb513e7d42493758cbcbb6429ed8904e1bc7fa52893e2680d5a79778","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-30T12:34:44Z","title_canon_sha256":"7d205ae59269763e4f1b882f0148b14e9c62b2bd1f57cab10915967e66289c9f"},"schema_version":"1.0","source":{"id":"2604.27792","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27792","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27792v3","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27792","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"EELNZ3PBX4TH","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"EELNZ3PBX4THLYKM","created_at":"2026-07-14T01:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"EELNZ3PB","created_at":"2026-07-14T01:22:07Z"}],"graph_snapshots":[{"event_id":"sha256:3e2f0a68396634eed2e6c122166d117e8cf62dbb0c37cdbf3a91a45966ab776e","target":"graph","created_at":"2026-07-14T01:22:07Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the three-stream Mixture-of-Transformers architecture under a UniDiffuser formulation, combined with the listed training data mixtures and post-training optimizations, produces the reported performance gains without hidden overfitting or benchmark-specific tuning that would not transfer to other robot platforms or tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MotuBrain jointly models video and action via a three-stream Mixture-of-Transformers UniDiffuser to reach 95.8-96.1% success on RoboTwin 2.0 benchmarks, top EWMScore, and fast 11 Hz inference while adapting to new robots with 50-100 trajectories."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single unified model achieves 95.8 percent success on complex robot tasks while adapting quickly to new embodiments."}],"snapshot_sha256":"3f44e7d87951c5efdbf100c97adccba2f3ba13db32103eeadffcb27b5a5a0a5b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T21:38:48.784012Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:53:43.788826Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27792/integrity.json","findings":[],"snapshot_sha256":"4087c4153b19a11457773160dc254d04e56c4576658394b282388d580fcacaa3","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, MotuBrain further introduces unified mu","authors_text":"Chendong Xiang, Fan Bao, Haitian Liu, Hengkai Tan, Hongzhe Bi, James Li, Jiabao Liu, Jingrui Pang, Jun Zhu, Kiro Jing, Louis Liu, Mengchen Cai, MotuBrain Team, Rongxu Cui, Runqing Wang, Ruowen Zhao, Shuhe Huang, Yao Feng, Yinze Rong, Zeyuan Wang","cross_cats":[],"headline":"A single unified model achieves 95.8 percent success on complex robot tasks while adapting quickly to new embodiments.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-30T12:34:44Z","title":"MotuBrain: An Advanced World Action Model for Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27792","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-07T05:39:13.885899Z","id":"58f4547f-2efa-4a66-959b-7d652ba30f17","model_set":{"reader":"grok-4.3"},"one_line_summary":"MotuBrain jointly models video and action via a three-stream Mixture-of-Transformers UniDiffuser to reach 95.8-96.1% success on RoboTwin 2.0 benchmarks, top EWMScore, and fast 11 Hz inference while adapting to new robots with 50-100 trajectories.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single unified model achieves 95.8 percent success on complex robot tasks while adapting quickly to new embodiments.","strongest_claim":"MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.","weakest_assumption":"The assumption that the three-stream Mixture-of-Transformers architecture under a UniDiffuser formulation, combined with the listed training data mixtures and post-training optimizations, produces the reported performance gains without hidden overfitting or benchmark-specific tuning that would not transfer to other robot platforms or tasks."}},"verdict_id":"58f4547f-2efa-4a66-959b-7d652ba30f17"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e0fe0df2bb33d845594f77ebebe5ac93919b9284f41ad00a7efcbf2c2a4a17ad","target":"record","created_at":"2026-07-14T01:22:07Z","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":"200189d0cb513e7d42493758cbcbb6429ed8904e1bc7fa52893e2680d5a79778","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-30T12:34:44Z","title_canon_sha256":"7d205ae59269763e4f1b882f0148b14e9c62b2bd1f57cab10915967e66289c9f"},"schema_version":"1.0","source":{"id":"2604.27792","kind":"arxiv","version":3}},"canonical_sha256":"2116dcede1bf2675e14c8ccaff0941fbd69e5eef6a0a7d1b1d392a13e81f7509","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2116dcede1bf2675e14c8ccaff0941fbd69e5eef6a0a7d1b1d392a13e81f7509","first_computed_at":"2026-07-14T01:22:07.617794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:07.617794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3f1Qqi/Rqd9lf0GMyDYsa3iSNYiZnPXNoJLIp42UqqZYJlRsneKl7XomGsD7GSEZGyi6PwzDADAtVqvP1uSqCw==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:07.618677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27792","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0fe0df2bb33d845594f77ebebe5ac93919b9284f41ad00a7efcbf2c2a4a17ad","sha256:3e2f0a68396634eed2e6c122166d117e8cf62dbb0c37cdbf3a91a45966ab776e"],"state_sha256":"3caf6de7f88fe38dad670c8692fe0078f9108ff9f0a0e72a38fe746ce713cb00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gnj+acymFcou7tvobjcCM8nCnHvHdqrL3B4qhJ+pxZcVeo0WTf0Odh+vU0Ih/MPzy+dSh085ImyuvPF+MfWmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:27:31.983292Z","bundle_sha256":"29f023eab9f078f047d088d82a90192267f43b1ae528ab7d3a46b06f20691944"}}