{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPO2M4HPXN3MU5RHWGU4F7KWIH","short_pith_number":"pith:CPO2M4HP","schema_version":"1.0","canonical_sha256":"13dda670efbb76ca7627b1a9c2fd5641daaae12514f8743d3ad8ab95f39d7db9","source":{"kind":"arxiv","id":"2410.15549","version":1},"attestation_state":"computed","paper":{"title":"A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"ByungOk Han, Jaehong Kim, Jinhyeok Jang","submitted_at":"2024-10-21T00:36:02Z","abstract_excerpt":"Vision-Language-Action (VLA) models are receiving increasing attention for their ability to enable robots to perform complex tasks by integrating visual context with linguistic commands. However, achieving efficient real-time performance remains challenging due to the high computational demands of existing models. To overcome this, we propose Dual Process VLA (DP-VLA), a hierarchical framework inspired by dual-process theory. DP-VLA utilizes a Large System 2 Model (L-Sys2) for complex reasoning and decision-making, while a Small System 1 Model (S-Sys1) handles real-time motor control and senso"},"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":"2410.15549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T00:36:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b3a82a4fcae98b402100d2b3d843bb97a32a04c0d4318a7c5bd9a5ade257b64b","abstract_canon_sha256":"a63da2664a25ee5226a075fcf35a1b43de50c48ae5d4be5701fea1b547badd66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:21.194904Z","signature_b64":"/5u1QT5uwW3LgX2Z57iPjn+5K7BFlePvP4pArLCNYsEQ6bD1AnLmevp989mRKR7AuLuuSlWewYQpjIMadC1DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13dda670efbb76ca7627b1a9c2fd5641daaae12514f8743d3ad8ab95f39d7db9","last_reissued_at":"2026-07-05T09:23:21.194447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:21.194447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"ByungOk Han, Jaehong Kim, Jinhyeok Jang","submitted_at":"2024-10-21T00:36:02Z","abstract_excerpt":"Vision-Language-Action (VLA) models are receiving increasing attention for their ability to enable robots to perform complex tasks by integrating visual context with linguistic commands. However, achieving efficient real-time performance remains challenging due to the high computational demands of existing models. To overcome this, we propose Dual Process VLA (DP-VLA), a hierarchical framework inspired by dual-process theory. DP-VLA utilizes a Large System 2 Model (L-Sys2) for complex reasoning and decision-making, while a Small System 1 Model (S-Sys1) handles real-time motor control and senso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15549","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/2410.15549/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":"2410.15549","created_at":"2026-07-05T09:23:21.194505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15549v1","created_at":"2026-07-05T09:23:21.194505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15549","created_at":"2026-07-05T09:23:21.194505+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPO2M4HPXN3M","created_at":"2026-07-05T09:23:21.194505+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPO2M4HPXN3MU5RH","created_at":"2026-07-05T09:23:21.194505+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPO2M4HP","created_at":"2026-07-05T09:23:21.194505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06018","citing_title":"RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures","ref_index":23,"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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31460","citing_title":"On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24642","citing_title":"Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22812","citing_title":"GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations","ref_index":13,"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":125,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16163","citing_title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02525","citing_title":"A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07514","citing_title":"Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH","json":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH.json","graph_json":"https://pith.science/api/pith-number/CPO2M4HPXN3MU5RHWGU4F7KWIH/graph.json","events_json":"https://pith.science/api/pith-number/CPO2M4HPXN3MU5RHWGU4F7KWIH/events.json","paper":"https://pith.science/paper/CPO2M4HP"},"agent_actions":{"view_html":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH","download_json":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH.json","view_paper":"https://pith.science/paper/CPO2M4HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15549&json=true","fetch_graph":"https://pith.science/api/pith-number/CPO2M4HPXN3MU5RHWGU4F7KWIH/graph.json","fetch_events":"https://pith.science/api/pith-number/CPO2M4HPXN3MU5RHWGU4F7KWIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH/action/storage_attestation","attest_author":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH/action/author_attestation","sign_citation":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH/action/citation_signature","submit_replication":"https://pith.science/pith/CPO2M4HPXN3MU5RHWGU4F7KWIH/action/replication_record"}},"created_at":"2026-07-05T09:23:21.194505+00:00","updated_at":"2026-07-05T09:23:21.194505+00:00"}