{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DEYOWYKECMJ7HFVJZO6LTGZPOU","short_pith_number":"pith:DEYOWYKE","schema_version":"1.0","canonical_sha256":"1930eb61441313f396a9cbbcb99b2f75024ac6763e22874f72528f983c545267","source":{"kind":"arxiv","id":"2509.00576","version":1},"attestation_state":"computed","paper":{"title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenhao Lu, Hang Zhao, Huazhe Xu, Jianning Cui, Jiyang Gao, Shuiqi Cheng, Tao Jiang, Tianyuan Yuan, Xiao Liu, Yicheng Liu","submitted_at":"2025-08-30T18:04:19Z","abstract_excerpt":"We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gathered using a consistent robotic embodiment, paired with precise subtask-level language annotations to facilitate both training and evaluation. Building on this dataset, we introduce G0, a dual-system framework that couples a Vision-Language Model (VLM) for multimodal planning with a Vision-Language-Action (VLA) model for fine-grained execution. G0 is trained using a three-stage curriculum: cross-embodiment pre-traini"},"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":"2509.00576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-30T18:04:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"478d8a370e1bade6d60ab5be33e09bf91425dc9ba62765a376a4af78a064991e","abstract_canon_sha256":"6eb3e51accbe14c545bb342c78d628ba1bce6ba8958ffa04bb460d06efdb78e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:18.856134Z","signature_b64":"3ZD7TSuXkU/DhyuqyUd9hBorMJDuTJ4qES3QZ+UYYTlJZ8nTdbYw4Rbby8/7B1nqZD93JjWgxEoX+SSc/jr3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1930eb61441313f396a9cbbcb99b2f75024ac6763e22874f72528f983c545267","last_reissued_at":"2026-07-05T12:02:18.855628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:18.855628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenhao Lu, Hang Zhao, Huazhe Xu, Jianning Cui, Jiyang Gao, Shuiqi Cheng, Tao Jiang, Tianyuan Yuan, Xiao Liu, Yicheng Liu","submitted_at":"2025-08-30T18:04:19Z","abstract_excerpt":"We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gathered using a consistent robotic embodiment, paired with precise subtask-level language annotations to facilitate both training and evaluation. Building on this dataset, we introduce G0, a dual-system framework that couples a Vision-Language Model (VLM) for multimodal planning with a Vision-Language-Action (VLA) model for fine-grained execution. G0 is trained using a three-stage curriculum: cross-embodiment pre-traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00576","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/2509.00576/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":"2509.00576","created_at":"2026-07-05T12:02:18.855689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00576v1","created_at":"2026-07-05T12:02:18.855689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00576","created_at":"2026-07-05T12:02:18.855689+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEYOWYKECMJ7","created_at":"2026-07-05T12:02:18.855689+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEYOWYKECMJ7HFVJ","created_at":"2026-07-05T12:02:18.855689+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEYOWYKE","created_at":"2026-07-05T12:02:18.855689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":37,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.06403","citing_title":"From Foundation to Application: Improving VLA Models in Practice","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06559","citing_title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05377","citing_title":"Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20562","citing_title":"MemoryWAM: Efficient World Action Modeling with Persistent Memory","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20521","citing_title":"HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18375","citing_title":"PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17846","citing_title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10267","citing_title":"What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08520","citing_title":"Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00678","citing_title":"ABot-M0.5: Unified Mobility-and-Manipulation World Action Model","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31286","citing_title":"DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30877","citing_title":"Wall-OSS-0.5 Technical Report","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31682","citing_title":"HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14752","citing_title":"X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27079","citing_title":"Trust Region Q Adjoint Matching","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27284","citing_title":"FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00113","citing_title":"World Models for Robotic Manipulation: A Survey","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14371","citing_title":"OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17441","citing_title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18692","citing_title":"A Pragmatic VLA Foundation Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11236","citing_title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU","json":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU.json","graph_json":"https://pith.science/api/pith-number/DEYOWYKECMJ7HFVJZO6LTGZPOU/graph.json","events_json":"https://pith.science/api/pith-number/DEYOWYKECMJ7HFVJZO6LTGZPOU/events.json","paper":"https://pith.science/paper/DEYOWYKE"},"agent_actions":{"view_html":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU","download_json":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU.json","view_paper":"https://pith.science/paper/DEYOWYKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00576&json=true","fetch_graph":"https://pith.science/api/pith-number/DEYOWYKECMJ7HFVJZO6LTGZPOU/graph.json","fetch_events":"https://pith.science/api/pith-number/DEYOWYKECMJ7HFVJZO6LTGZPOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU/action/storage_attestation","attest_author":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU/action/author_attestation","sign_citation":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU/action/citation_signature","submit_replication":"https://pith.science/pith/DEYOWYKECMJ7HFVJZO6LTGZPOU/action/replication_record"}},"created_at":"2026-07-05T12:02:18.855689+00:00","updated_at":"2026-07-05T12:02:18.855689+00:00"}