{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GNQPJI4STITBXFP7ZUCQA7D4F7","short_pith_number":"pith:GNQPJI4S","schema_version":"1.0","canonical_sha256":"3360f4a3929a261b95ffcd05007c7c2fdf99d14c8a47b913f375957d457a151f","source":{"kind":"arxiv","id":"2508.05635","version":3},"attestation_state":"computed","paper":{"title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A single instruction-conditioned video diffusion model unifies policy learning, simulation, and evaluation for robotic manipulation.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Donglin Yang, Guanghui Ren, Jianlan Luo, Jingbin Cai, Liliang Chen, Maoqing Yao, Pengfei Zhou, Shengcong Chen, Shuicheng Yan, Si Liu, Siyuan Huang, Yue Hu, Yue Liao, Yuxin Jiang","submitted_at":"2025-08-07T17:59:44Z","abstract_excerpt":"We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-generative framework. At its core, GE-Base is a large-scale, instruction-conditioned video diffusion model that captures the spatial, temporal, and semantic dynamics of real-world robotic interactions in a structured latent space. Built upon this foundation, GE-Act maps latent representations to executable action trajectories through a lightweight, flow-matching decoder, enabling precise and generalizable policy infer"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2508.05635","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-07T17:59:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5328146171b55d888e894fcfc9a7a0b678ebab9e88c800f3a863ca6e1cdc1e83","abstract_canon_sha256":"97caad6ad19a11beb1bd896fc1d5c61e7b25d856f5a70d6c789693cb7c831960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.108063Z","signature_b64":"qLqfYECj02PnANpqXDw8tF91fDJcxzpr8qYoT99o1qMPtVDV1MQfb9kxapvBV1rIWIjnOgqIG4vK1KAOjazBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3360f4a3929a261b95ffcd05007c7c2fdf99d14c8a47b913f375957d457a151f","last_reissued_at":"2026-05-17T23:38:50.107568Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.107568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A single instruction-conditioned video diffusion model unifies policy learning, simulation, and evaluation for robotic manipulation.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Donglin Yang, Guanghui Ren, Jianlan Luo, Jingbin Cai, Liliang Chen, Maoqing Yao, Pengfei Zhou, Shengcong Chen, Shuicheng Yan, Si Liu, Siyuan Huang, Yue Hu, Yue Liao, Yuxin Jiang","submitted_at":"2025-08-07T17:59:44Z","abstract_excerpt":"We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-generative framework. At its core, GE-Base is a large-scale, instruction-conditioned video diffusion model that captures the spatial, temporal, and semantic dynamics of real-world robotic interactions in a structured latent space. Built upon this foundation, GE-Act maps latent representations to executable action trajectories through a lightweight, flow-matching decoder, enabling precise and generalizable policy infer"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GE integrates policy learning, evaluation, and simulation within a single video-generative framework, establishing a scalable and practical foundation for instruction-driven, general-purpose embodied intelligence.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the instruction-conditioned video diffusion model in GE-Base sufficiently captures real-world spatial, temporal, and semantic dynamics to support accurate action mapping in GE-Act and reliable rollouts in GE-Sim across diverse embodiments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Genie Envisioner unifies robotic policy learning, simulation, and evaluation inside one instruction-conditioned video diffusion framework using GE-Base, GE-Act, and GE-Sim.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single instruction-conditioned video diffusion model unifies policy learning, simulation, and evaluation for robotic manipulation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d31d1636b651700f6bf1f02c37ac00c072cd4e1ffb5b464d089e336ff31020e2"},"source":{"id":"2508.05635","kind":"arxiv","version":3},"verdict":{"id":"bb69e79f-dc32-49f2-8af2-395ef5156751","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:25:20.398637Z","strongest_claim":"GE integrates policy learning, evaluation, and simulation within a single video-generative framework, establishing a scalable and practical foundation for instruction-driven, general-purpose embodied intelligence.","one_line_summary":"Genie Envisioner unifies robotic policy learning, simulation, and evaluation inside one instruction-conditioned video diffusion framework using GE-Base, GE-Act, and GE-Sim.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the instruction-conditioned video diffusion model in GE-Base sufficiently captures real-world spatial, temporal, and semantic dynamics to support accurate action mapping in GE-Act and reliable rollouts in GE-Sim across diverse embodiments.","pith_extraction_headline":"A single instruction-conditioned video diffusion model unifies policy learning, simulation, and evaluation for robotic manipulation."},"references":{"count":30,"sample":[{"doi":"","year":null,"title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","work_id":"83956045-536a-41ff-af02-b80e2a614eab","ref_index":1,"cited_arxiv_id":"2503.01743","is_internal_anchor":true},{"doi":"","year":null,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","ref_index":2,"cited_arxiv_id":"2501.03575","is_internal_anchor":true},{"doi":"","year":null,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":3,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":null,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":4,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":null,"title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","work_id":"e2db69c7-ee8a-4cb7-a761-7b8de1dfcf97","ref_index":5,"cited_arxiv_id":"2503.14734","is_internal_anchor":true}],"resolved_work":30,"snapshot_sha256":"ce8e3f6dd0408b02de1dc50f3f6352fe12ada7f544123ab7fa4124bd82b284f4","internal_anchors":20},"formal_canon":{"evidence_count":3,"snapshot_sha256":"d20f84f0c4517f6d64e62745072350500c0426fae96871ae5042365b95690e42"},"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":"2508.05635","created_at":"2026-05-17T23:38:50.107645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05635v3","created_at":"2026-05-17T23:38:50.107645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05635","created_at":"2026-05-17T23:38:50.107645+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNQPJI4STITB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNQPJI4STITBXFP7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNQPJI4S","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":139,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17912","citing_title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18556","citing_title":"Key-Gram: Extensible World Knowledge for Embodied Manipulation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2603.12639","citing_title":"RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2510.13778","citing_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16666","citing_title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16163","citing_title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27792","citing_title":"MotuBrain: An Advanced World Action Model for Robot Control","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15922","citing_title":"World Action Models are Zero-shot Policies","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00078","citing_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21741","citing_title":"Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19683","citing_title":"Mask World Model: Predicting What Matters for Robust Robot Policy Learning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11351","citing_title":"WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05498","citing_title":"JailWAM: Jailbreaking World Action Models in Robot Control","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11751","citing_title":"Grounded World Model for Semantically Generalizable Planning","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14732","citing_title":"World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7","json":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7.json","graph_json":"https://pith.science/api/pith-number/GNQPJI4STITBXFP7ZUCQA7D4F7/graph.json","events_json":"https://pith.science/api/pith-number/GNQPJI4STITBXFP7ZUCQA7D4F7/events.json","paper":"https://pith.science/paper/GNQPJI4S"},"agent_actions":{"view_html":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7","download_json":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7.json","view_paper":"https://pith.science/paper/GNQPJI4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05635&json=true","fetch_graph":"https://pith.science/api/pith-number/GNQPJI4STITBXFP7ZUCQA7D4F7/graph.json","fetch_events":"https://pith.science/api/pith-number/GNQPJI4STITBXFP7ZUCQA7D4F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7/action/storage_attestation","attest_author":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7/action/author_attestation","sign_citation":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7/action/citation_signature","submit_replication":"https://pith.science/pith/GNQPJI4STITBXFP7ZUCQA7D4F7/action/replication_record"}},"created_at":"2026-05-17T23:38:50.107645+00:00","updated_at":"2026-05-17T23:38:50.107645+00:00"}