{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N4KIGEJWUB2G6R3SXRNOP5J3J5","short_pith_number":"pith:N4KIGEJW","schema_version":"1.0","canonical_sha256":"6f14831136a0746f4772bc5ae7f53b4f5673cdfa4cf33db07789c8c259e8be85","source":{"kind":"arxiv","id":"2505.03912","version":1},"attestation_state":"computed","paper":{"title":"OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bofang Jia, Can Cui, Donglin Wang, Han Zhao, Pengxiang Ding, Runze Suo, Shuanghao Bai, Siteng Huang, Wanqi Zhou, Wenxuan Song, Xinyang Tong, Yang Liu, Zirui Ge","submitted_at":"2025-05-06T18:35:07Z","abstract_excerpt":"Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further performance analysis and optimization. To address this problem, this paper will summarize and compare the structural designs of existing dual-system architectures, and conduct systematic empirical evaluations on the core design elements of existing dual-system architectures. Ultimately, it will provide a low-cost open-source model for further exploration. Of course, this project will continue to update with more experim"},"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":"2505.03912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-06T18:35:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"74481d77963e2cb3699d4f8bbec395c8c34bafca7157ff629ab130bbc72a38a2","abstract_canon_sha256":"7fa53aec5455cd10933a95ef1350a927dec13cb11cabd7ffa6186d36558cade8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:33.740038Z","signature_b64":"eU09IRXhKN0i+ermrsHJor/ovQk5NQv011Z6Nqx3dhMBH44WdrcHqT5qrYEvzZIGP8tgVeJQq64rASPJrCbdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f14831136a0746f4772bc5ae7f53b4f5673cdfa4cf33db07789c8c259e8be85","last_reissued_at":"2026-07-05T10:59:33.739542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:33.739542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bofang Jia, Can Cui, Donglin Wang, Han Zhao, Pengxiang Ding, Runze Suo, Shuanghao Bai, Siteng Huang, Wanqi Zhou, Wenxuan Song, Xinyang Tong, Yang Liu, Zirui Ge","submitted_at":"2025-05-06T18:35:07Z","abstract_excerpt":"Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further performance analysis and optimization. To address this problem, this paper will summarize and compare the structural designs of existing dual-system architectures, and conduct systematic empirical evaluations on the core design elements of existing dual-system architectures. Ultimately, it will provide a low-cost open-source model for further exploration. Of course, this project will continue to update with more experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03912","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/2505.03912/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":"2505.03912","created_at":"2026-07-05T10:59:33.739603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03912v1","created_at":"2026-07-05T10:59:33.739603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03912","created_at":"2026-07-05T10:59:33.739603+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4KIGEJWUB2G","created_at":"2026-07-05T10:59:33.739603+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4KIGEJWUB2G6R3S","created_at":"2026-07-05T10:59:33.739603+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4KIGEJW","created_at":"2026-07-05T10:59:33.739603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22794","citing_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12366","citing_title":"APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06155","citing_title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29570","citing_title":"Hierarchical Policy Learning via Spectral Decomposition","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25802","citing_title":"Rethinking VLM Representation for VLA Initialization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04978","citing_title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","ref_index":229,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15669","citing_title":"DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01581","citing_title":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15620","citing_title":"Towards Generalizable Robotic Manipulation in Dynamic Environments","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25661","citing_title":"Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26320","citing_title":"DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13382","citing_title":"BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10921","citing_title":"RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24182","citing_title":"$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05672","citing_title":"A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20834","citing_title":"PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5","json":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5.json","graph_json":"https://pith.science/api/pith-number/N4KIGEJWUB2G6R3SXRNOP5J3J5/graph.json","events_json":"https://pith.science/api/pith-number/N4KIGEJWUB2G6R3SXRNOP5J3J5/events.json","paper":"https://pith.science/paper/N4KIGEJW"},"agent_actions":{"view_html":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5","download_json":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5.json","view_paper":"https://pith.science/paper/N4KIGEJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03912&json=true","fetch_graph":"https://pith.science/api/pith-number/N4KIGEJWUB2G6R3SXRNOP5J3J5/graph.json","fetch_events":"https://pith.science/api/pith-number/N4KIGEJWUB2G6R3SXRNOP5J3J5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5/action/storage_attestation","attest_author":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5/action/author_attestation","sign_citation":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5/action/citation_signature","submit_replication":"https://pith.science/pith/N4KIGEJWUB2G6R3SXRNOP5J3J5/action/replication_record"}},"created_at":"2026-07-05T10:59:33.739603+00:00","updated_at":"2026-07-05T10:59:33.739603+00:00"}