{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UCFL54T5TYCJIGF4EG4OUKZIID","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":"b93945cdd00928251a5e5d498e11d02981f54dfc1915fba1b499718dfc9f733a","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T08:31:55Z","title_canon_sha256":"fa3c128f8b8583963347041a1d34688c91ca0ea5ec73addaaa8e286d2aaa09b0"},"schema_version":"1.0","source":{"id":"2507.12898","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12898","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12898v4","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12898","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"UCFL54T5TYCJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UCFL54T5TYCJIGF4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UCFL54T5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:310c9ea042dde8472f90361688b332ff596ea2c4a180dd6cc753fbea3987750f","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"With only 20 minutes of human demonstrations on an unseen robot (1% of typical data), Vidar outperforms state-of-the-art baselines and generalizes to unseen tasks, backgrounds, and camera layouts."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That continuous pre-training of an internet-scale video diffusion model on 750K trajectories from only three robot platforms produces a sufficiently general visual-dynamics prior that can be grounded to arbitrary new embodiments via a lightweight masked inverse dynamics adapter."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations."}],"snapshot_sha256":"c0533665f2f93f4230fdbfa435f80abef7506b75c76ee93708999befbbe66809"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"836e78ec6461bff8a138f46abccd699d4b599eb8df19712fe6821ad38c1f73dc"},"paper":{"abstract_excerpt":"Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint shifts. Based on previous advances in video-based robot control, we present Vidar, consisting of an embodied video diffusion model as the generalizable prior and a masked inverse dynamics model (MIDM) as the adapter. We leverage a video diffusion model pre-trained at Internet scale, and further continuously pre-train it for the embodied domain using 750K multi-vi","authors_text":"Chendong Xiang, Guodong Liu, Hang Su, Hengkai Tan, Jun Zhu, Shuhe Huang, Xinyi Mao, Yao Feng","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T08:31:55Z","title":"Vidar: Embodied Video Diffusion Model for Generalist Manipulation"},"references":{"count":46,"internal_anchors":20,"resolved_work":46,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration","work_id":"5e1215f6-254f-4463-b555-ef06efc0e71d","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"OpenVLA: An Open-Source Vision-Language-Action Model","work_id":"c58a80f3-556e-4070-8e8e-8969c4f0a263","year":2024},{"cited_arxiv_id":"2410.07864","doi":"","is_internal_anchor":true,"ref_index":3,"title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","work_id":"12319725-bc7d-4c32-a229-ad270a7460bc","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Crossformer: Transformer Utilizing Cross-Dimension Depen- dency for Multivariate Time Series Forecasting","work_id":"fbe803e5-9aa0-4f94-8c82-4c3eab7b9890","year":2023},{"cited_arxiv_id":"2504.16054","doi":"","is_internal_anchor":true,"ref_index":5,"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","year":2025}],"snapshot_sha256":"45cd919227676cd242ef839aeb74f4319d3c288045301f80474c8cf998cff2fc"},"source":{"id":"2507.12898","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-16T09:50:48.324061Z","id":"47d47346-9e8c-4074-9134-099faeccb479","model_set":{"reader":"grok-4.3"},"one_line_summary":"Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations.","strongest_claim":"With only 20 minutes of human demonstrations on an unseen robot (1% of typical data), Vidar outperforms state-of-the-art baselines and generalizes to unseen tasks, backgrounds, and camera layouts.","weakest_assumption":"That continuous pre-training of an internet-scale video diffusion model on 750K trajectories from only three robot platforms produces a sufficiently general visual-dynamics prior that can be grounded to arbitrary new embodiments via a lightweight masked inverse dynamics adapter."}},"verdict_id":"47d47346-9e8c-4074-9134-099faeccb479"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c9e9285e048e4e44c1e54d231294357045c384bd736092f053b0c18763a262a2","target":"record","created_at":"2026-05-17T23:38:48Z","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":"b93945cdd00928251a5e5d498e11d02981f54dfc1915fba1b499718dfc9f733a","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T08:31:55Z","title_canon_sha256":"fa3c128f8b8583963347041a1d34688c91ca0ea5ec73addaaa8e286d2aaa09b0"},"schema_version":"1.0","source":{"id":"2507.12898","kind":"arxiv","version":4}},"canonical_sha256":"a08abef27d9e049418bc21b8ea2b2840fd028bb99319803a1c9b926dadbd5add","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a08abef27d9e049418bc21b8ea2b2840fd028bb99319803a1c9b926dadbd5add","first_computed_at":"2026-05-17T23:38:48.275613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.275613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F3/z76/qDuG/SfZcfBA5bw0VZyNt8m+LtcCH4IRt7VQkXXXR5L+vhBUSP9NCMyn3ACDAJ9y55Lxs0umT88bFBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.276091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12898","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9e9285e048e4e44c1e54d231294357045c384bd736092f053b0c18763a262a2","sha256:310c9ea042dde8472f90361688b332ff596ea2c4a180dd6cc753fbea3987750f"],"state_sha256":"94ff5e5f658a4a3f0e1a2f40036ad77df928281b802df20c8fe1a68346d7dfca"}