{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N474HSTI5WGNJDOAUGXIBMO6YA","short_pith_number":"pith:N474HSTI","schema_version":"1.0","canonical_sha256":"6f3fc3ca68ed8cd48dc0a1ae80b1dec000eec2076c1bf52664f01aac18095859","source":{"kind":"arxiv","id":"2506.01953","version":1},"attestation_state":"computed","paper":{"title":"Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenyang Gu, Chi-Wing Fu, Hao Chen, Jiaming Liu, Pheng-Ann Heng, Renrui Zhang, Shanghang Zhang, Xiao He, Xiaoqi Li, Yandong Guo, Zhuoyang Liu","submitted_at":"2025-06-02T17:59:51Z","abstract_excerpt":"Generalized policy and execution efficiency constitute the two critical challenges in robotic manipulation. While recent foundation policies benefit from the common-sense reasoning capabilities of internet-scale pretrained vision-language models (VLMs), they often suffer from low execution frequency. To mitigate this dilemma, dual-system approaches, inspired by Kahneman's theory, have been proposed to leverage a VLM-based System 2 model handling high-level reasoning and a separate System 1 action model ensuring real-time control. However, existing designs maintain both systems as separate mode"},"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":"2506.01953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-02T17:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"5fa1b7fa4583268e4800b373bd15dd83ba6ab3eb5db7b0741ff7c58f799888fb","abstract_canon_sha256":"ba9f0e101f7499a036b17a0174c88d84958bbc5a72bb76f0f3e5a9418d1c8fe8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:22.016096Z","signature_b64":"cD+c90TJv/ZyUocVm9jUwof2qTRpL1ScNoNNRidDWZ4twnVKKiFfNb4Aok0ge89Wtce3LkaU+DH7e5FJiPR0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f3fc3ca68ed8cd48dc0a1ae80b1dec000eec2076c1bf52664f01aac18095859","last_reissued_at":"2026-07-05T11:14:22.015627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:22.015627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenyang Gu, Chi-Wing Fu, Hao Chen, Jiaming Liu, Pheng-Ann Heng, Renrui Zhang, Shanghang Zhang, Xiao He, Xiaoqi Li, Yandong Guo, Zhuoyang Liu","submitted_at":"2025-06-02T17:59:51Z","abstract_excerpt":"Generalized policy and execution efficiency constitute the two critical challenges in robotic manipulation. While recent foundation policies benefit from the common-sense reasoning capabilities of internet-scale pretrained vision-language models (VLMs), they often suffer from low execution frequency. To mitigate this dilemma, dual-system approaches, inspired by Kahneman's theory, have been proposed to leverage a VLM-based System 2 model handling high-level reasoning and a separate System 1 action model ensuring real-time control. However, existing designs maintain both systems as separate mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01953","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/2506.01953/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":"2506.01953","created_at":"2026-07-05T11:14:22.015681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01953v1","created_at":"2026-07-05T11:14:22.015681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01953","created_at":"2026-07-05T11:14:22.015681+00:00"},{"alias_kind":"pith_short_12","alias_value":"N474HSTI5WGN","created_at":"2026-07-05T11:14:22.015681+00:00"},{"alias_kind":"pith_short_16","alias_value":"N474HSTI5WGNJDOA","created_at":"2026-07-05T11:14:22.015681+00:00"},{"alias_kind":"pith_short_8","alias_value":"N474HSTI","created_at":"2026-07-05T11:14:22.015681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06564","citing_title":"Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05396","citing_title":"From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23685","citing_title":"LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22794","citing_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20905","citing_title":"Vesta: A Generalist Embodied Reasoning Model","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17055","citing_title":"T-Rex: Tactile-Reactive Dexterous Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01804","citing_title":"VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02501","citing_title":"Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31723","citing_title":"UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30686","citing_title":"Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning","ref_index":15,"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":7,"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":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09023","citing_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","ref_index":6,"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":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":40,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04161","citing_title":"Adaptive Action Chunking at Inference-time for Vision-Language-Action Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10942","citing_title":"HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":9,"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":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA","json":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA.json","graph_json":"https://pith.science/api/pith-number/N474HSTI5WGNJDOAUGXIBMO6YA/graph.json","events_json":"https://pith.science/api/pith-number/N474HSTI5WGNJDOAUGXIBMO6YA/events.json","paper":"https://pith.science/paper/N474HSTI"},"agent_actions":{"view_html":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA","download_json":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA.json","view_paper":"https://pith.science/paper/N474HSTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01953&json=true","fetch_graph":"https://pith.science/api/pith-number/N474HSTI5WGNJDOAUGXIBMO6YA/graph.json","fetch_events":"https://pith.science/api/pith-number/N474HSTI5WGNJDOAUGXIBMO6YA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA/action/storage_attestation","attest_author":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA/action/author_attestation","sign_citation":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA/action/citation_signature","submit_replication":"https://pith.science/pith/N474HSTI5WGNJDOAUGXIBMO6YA/action/replication_record"}},"created_at":"2026-07-05T11:14:22.015681+00:00","updated_at":"2026-07-05T11:14:22.015681+00:00"}