{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4FABLZ2EHQTWUHSJT6OWVVEHKK","short_pith_number":"pith:4FABLZ2E","schema_version":"1.0","canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","source":{"kind":"arxiv","id":"2406.16862","version":1},"attestation_state":"computed","paper":{"title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Achal Dave, Carl Vondrick, Ege Ozguroglu, Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Shuran Song, Sruthi Sudhakar","submitted_at":"2024-06-24T17:59:45Z","abstract_excerpt":"A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of internet videos. In this paper, we propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. At test time, we generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot. Our key insig"},"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":"2406.16862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-24T17:59:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b345b7bc789d0771251aefb7731d2dcdfd7350079959a4cdaedb6338b44e94df","abstract_canon_sha256":"ca16d16a445fd2ab8f1352dd456f3b1b9d6bc71dd84069aabe63afa8bfcfce4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:04.681441Z","signature_b64":"1me0iFL8fuwLxDWkOS7Emyfh5ULBNSTcLAw9XPgQTM+uyKijdfkbjZQiigtYSbPhlW2F0ffL/h7WeUIVmXb6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","last_reissued_at":"2026-07-05T08:36:04.680964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:04.680964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Achal Dave, Carl Vondrick, Ege Ozguroglu, Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Shuran Song, Sruthi Sudhakar","submitted_at":"2024-06-24T17:59:45Z","abstract_excerpt":"A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of internet videos. In this paper, we propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. At test time, we generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot. Our key insig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16862","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/2406.16862/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":"2406.16862","created_at":"2026-07-05T08:36:04.681022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16862v1","created_at":"2026-07-05T08:36:04.681022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16862","created_at":"2026-07-05T08:36:04.681022+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FABLZ2EHQTW","created_at":"2026-07-05T08:36:04.681022+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FABLZ2EHQTWUHSJ","created_at":"2026-07-05T08:36:04.681022+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FABLZ2E","created_at":"2026-07-05T08:36:04.681022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06559","citing_title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22136","citing_title":"Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19340","citing_title":"ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11187","citing_title":"Next Forcing: Causal World Modeling with Multi-Chunk Prediction","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04811","citing_title":"Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15032","citing_title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28816","citing_title":"Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01099","citing_title":"Geometry-aware 4D Video Generation for Robot Manipulation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15692","citing_title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK","json":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK.json","graph_json":"https://pith.science/api/pith-number/4FABLZ2EHQTWUHSJT6OWVVEHKK/graph.json","events_json":"https://pith.science/api/pith-number/4FABLZ2EHQTWUHSJT6OWVVEHKK/events.json","paper":"https://pith.science/paper/4FABLZ2E"},"agent_actions":{"view_html":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK","download_json":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK.json","view_paper":"https://pith.science/paper/4FABLZ2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16862&json=true","fetch_graph":"https://pith.science/api/pith-number/4FABLZ2EHQTWUHSJT6OWVVEHKK/graph.json","fetch_events":"https://pith.science/api/pith-number/4FABLZ2EHQTWUHSJT6OWVVEHKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/action/storage_attestation","attest_author":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/action/author_attestation","sign_citation":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/action/citation_signature","submit_replication":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/action/replication_record"}},"created_at":"2026-07-05T08:36:04.681022+00:00","updated_at":"2026-07-05T08:36:04.681022+00:00"}