{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:32JR5VRRFUQIHJGYXJ7GWIS5VD","short_pith_number":"pith:32JR5VRR","schema_version":"1.0","canonical_sha256":"de931ed6312d2083a4d8ba7e6b225da8f9ab48292d1e3ea0052dfc4936a1357e","source":{"kind":"arxiv","id":"2410.08001","version":3},"attestation_state":"computed","paper":{"title":"Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Heming Cui, Hongyang Li, Jia Zeng, Jisong Cai, Li Chen, Maoqing Yao, Qingwen Bu, Yu Qiao","submitted_at":"2024-10-10T14:57:51Z","abstract_excerpt":"The increasing demand for versatile robotic systems to operate in diverse and dynamic environments has emphasized the importance of a generalist policy, which leverages a large cross-embodiment data corpus to facilitate broad adaptability and high-level reasoning. However, the generalist would struggle with inefficient inference and cost-expensive training. The specialist policy, instead, is curated for specific domain data and excels at task-level precision with efficiency. Yet, it lacks the generalization capacity for a wide range of applications. Inspired by these observations, we introduce"},"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":"2410.08001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-10T14:57:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8187a2a09782dca7bd1b1f260549e4ceeb5f7b937a760d4f02c2a57f8d0a4cea","abstract_canon_sha256":"9e09da82e13f210addc61b7f7b3a02a8827c5849d3952e31424cfc44e8287b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:28.392382Z","signature_b64":"C4OX8kWrEajyVYizuoAQr8iteL7EFFbsMpbsjcmMvl4s8l7N1aMVYdF3yn2T0ulbXTMAQoZ3H0GC0t1YM7BMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de931ed6312d2083a4d8ba7e6b225da8f9ab48292d1e3ea0052dfc4936a1357e","last_reissued_at":"2026-07-05T10:10:28.391884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:28.391884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Heming Cui, Hongyang Li, Jia Zeng, Jisong Cai, Li Chen, Maoqing Yao, Qingwen Bu, Yu Qiao","submitted_at":"2024-10-10T14:57:51Z","abstract_excerpt":"The increasing demand for versatile robotic systems to operate in diverse and dynamic environments has emphasized the importance of a generalist policy, which leverages a large cross-embodiment data corpus to facilitate broad adaptability and high-level reasoning. However, the generalist would struggle with inefficient inference and cost-expensive training. The specialist policy, instead, is curated for specific domain data and excels at task-level precision with efficiency. Yet, it lacks the generalization capacity for a wide range of applications. Inspired by these observations, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08001","kind":"arxiv","version":3},"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/2410.08001/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":"2410.08001","created_at":"2026-07-05T10:10:28.391939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08001v3","created_at":"2026-07-05T10:10:28.391939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08001","created_at":"2026-07-05T10:10:28.391939+00:00"},{"alias_kind":"pith_short_12","alias_value":"32JR5VRRFUQI","created_at":"2026-07-05T10:10:28.391939+00:00"},{"alias_kind":"pith_short_16","alias_value":"32JR5VRRFUQIHJGY","created_at":"2026-07-05T10:10:28.391939+00:00"},{"alias_kind":"pith_short_8","alias_value":"32JR5VRR","created_at":"2026-07-05T10:10:28.391939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05377","citing_title":"Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22794","citing_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","ref_index":5,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09827","citing_title":"MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09811","citing_title":"AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31460","citing_title":"On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25547","citing_title":"TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25829","citing_title":"OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20200","citing_title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","ref_index":2,"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":126,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":289,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06111","citing_title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14125","citing_title":"HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06669","citing_title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14125","citing_title":"HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD","json":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD.json","graph_json":"https://pith.science/api/pith-number/32JR5VRRFUQIHJGYXJ7GWIS5VD/graph.json","events_json":"https://pith.science/api/pith-number/32JR5VRRFUQIHJGYXJ7GWIS5VD/events.json","paper":"https://pith.science/paper/32JR5VRR"},"agent_actions":{"view_html":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD","download_json":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD.json","view_paper":"https://pith.science/paper/32JR5VRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08001&json=true","fetch_graph":"https://pith.science/api/pith-number/32JR5VRRFUQIHJGYXJ7GWIS5VD/graph.json","fetch_events":"https://pith.science/api/pith-number/32JR5VRRFUQIHJGYXJ7GWIS5VD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD/action/storage_attestation","attest_author":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD/action/author_attestation","sign_citation":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD/action/citation_signature","submit_replication":"https://pith.science/pith/32JR5VRRFUQIHJGYXJ7GWIS5VD/action/replication_record"}},"created_at":"2026-07-05T10:10:28.391939+00:00","updated_at":"2026-07-05T10:10:28.391939+00:00"}