{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PJU6IWRD6PMWYZPP66ML6CSIRS","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":"83090a0b7e213a14395a56990cba1bc5989cb4fdb3ad92e464a98152840b7853","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T18:49:43Z","title_canon_sha256":"150dec8e0282a7e6db552a244369c04eb2de1c00c818ae3ac60e8cb4564082bd"},"schema_version":"1.0","source":{"id":"2602.06949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06949","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06949v1","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06949","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"PJU6IWRD6PMW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PJU6IWRD6PMWYZPP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PJU6IWRD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2f7657330051f08883676f12f9236005646fa7a46af84b58e8cb1728201a02fd","target":"graph","created_at":"2026-05-17T23:38:47Z","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":"After post-training on small-scale target robot data, DreamDojo demonstrates a strong understanding of physics and precise action controllability on multiple challenging out-of-distribution benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Continuous latent actions learned from unlabeled human videos serve as effective proxy actions that transfer interaction knowledge to robot control without introducing domain gaps that degrade physics prediction."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A world model pretrained on 44k hours of human videos transfers to robots with accurate physics and control after minimal fine-tuning."}],"snapshot_sha256":"a3f8b110174c6ec88df86769ff4a233a458c004e8bf65bc5a131f5a317ea95c0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"794471e644fdf17259b3fb559808e7fe8b674f03f6f388a7f5f4c9a082bf2898"},"paper":{"abstract_excerpt":"Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant challenges due to limited data coverage and scarce action labels. As an endeavor towards this end, we introduce DreamDojo, a foundation world model that learns diverse interactions and dexterous controls from 44k hours of egocentric human videos. Our data mixture represents the largest video dataset to date for world model pretraining, spanning a wide range of da","authors_text":"Ayaan Malik, Chen-Hsuan Lin, Dantong Niu, George Kurian, Jiannan Xiang, Jinwei Gu, Jitendra Malik, Joel Jang, Jun Zhang, Kaichun Mo, Kaiyuan Zheng, K.R. Zentner, Linxi \"Jim\" Fan, Loic Magne, Ming-Yu Liu, Pieter Abbeel, Pooya Jannaty, Qianli Ma, Ruijie Zheng, Seonghyeon Ye, Seungjun Nah, Shenyuan Gao, Sihyun Yu, Suneel Indupuru, Wei-Cheng Tseng, William Liang, You Liang Tan, Yuke Zhu, Yuqi Xie, Yuzhu Dong","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"A world model pretrained on 44k hours of human videos transfers to robots with accurate physics and control after minimal fine-tuning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T18:49:43Z","title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos"},"references":{"count":131,"internal_anchors":30,"resolved_work":131,"sample":[{"cited_arxiv_id":"2511.00062","doi":"","is_internal_anchor":true,"ref_index":1,"title":"World Simulation with Video Foundation Models for Physical AI","work_id":"1dc393b8-98c3-43bd-8ab0-25d7c2a9705b","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Diffusion for World Modeling: Visual Details Matter in Atari","work_id":"0b950347-c858-49b3-b5b8-7d4ef86b8c79","year":2024},{"cited_arxiv_id":"2506.09985","doi":"","is_internal_anchor":true,"ref_index":3,"title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","work_id":"a9c28401-f16a-4933-89f0-788e2f94e52b","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Whole-body conditioned egocentric video prediction","work_id":"16a86800-0171-422d-8be4-1732d118a0d4","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Genie 3: A New Frontier for World Models, 2025","work_id":"91fae91f-bd0b-44af-994d-847d340d4483","year":2025}],"snapshot_sha256":"8f97820ce321d473360d79e6c75b7013256917ad3f28093817fed9068a36e900"},"source":{"id":"2602.06949","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T16:57:28.111782Z","id":"366f8ffd-3847-47a6-a304-e2f563a32b85","model_set":{"reader":"grok-4.3"},"one_line_summary":"DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A world model pretrained on 44k hours of human videos transfers to robots with accurate physics and control after minimal fine-tuning.","strongest_claim":"After post-training on small-scale target robot data, DreamDojo demonstrates a strong understanding of physics and precise action controllability on multiple challenging out-of-distribution benchmarks.","weakest_assumption":"Continuous latent actions learned from unlabeled human videos serve as effective proxy actions that transfer interaction knowledge to robot control without introducing domain gaps that degrade physics prediction."}},"verdict_id":"366f8ffd-3847-47a6-a304-e2f563a32b85"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3d5c569469ed356b37a933bf1483b9fc01a62603015f53a03edec327e4619ab7","target":"record","created_at":"2026-05-17T23:38:47Z","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":"83090a0b7e213a14395a56990cba1bc5989cb4fdb3ad92e464a98152840b7853","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T18:49:43Z","title_canon_sha256":"150dec8e0282a7e6db552a244369c04eb2de1c00c818ae3ac60e8cb4564082bd"},"schema_version":"1.0","source":{"id":"2602.06949","kind":"arxiv","version":1}},"canonical_sha256":"7a69e45a23f3d96c65eff798bf0a488c8a2a7b9eb7b175fa9bd5fb26d25d470c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a69e45a23f3d96c65eff798bf0a488c8a2a7b9eb7b175fa9bd5fb26d25d470c","first_computed_at":"2026-05-17T23:38:47.189361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.189361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rzHn06Js4XfbHHx+VLlxGOOwY3zyWgaiZeQu37KLz5GYw2iazAXU2S4r9vbtIL1pQvLH447zySdJ00xNILhDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.189776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d5c569469ed356b37a933bf1483b9fc01a62603015f53a03edec327e4619ab7","sha256:2f7657330051f08883676f12f9236005646fa7a46af84b58e8cb1728201a02fd"],"state_sha256":"6a9828ae8143681e264d6764cdd2fb4daad3cf878b8075f8badc86da45a49d75"}