{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DZPXZUR5OOX3CZUMLH6UTXDGNP","short_pith_number":"pith:DZPXZUR5","schema_version":"1.0","canonical_sha256":"1e5f7cd23d73afb1668c59fd49dc666be6a2b7a9d0d4594de0a76160313dd672","source":{"kind":"arxiv","id":"2503.02881","version":3},"attestation_state":"computed","paper":{"title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Guoying Gu, Gu Zhang, Han Xue, Huazhe Xu, Jieji Ren, Wendi Chen, Yuan Fang","submitted_at":"2025-03-04T18:58:21Z","abstract_excerpt":"Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces; however, this remains challenging for robots. Existing visual imitation learning (IL) approaches rely on action chunking to model complex behaviors, which lacks the ability to respond instantly to real-time tactile feedback during the chunk execution. Furthermore, most teleoperation systems struggle to provide fine-grained tactile / force feedback, which limits the range of tasks that can be performed. To ad"},"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":"2503.02881","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-04T18:58:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"daad7cab2ce42d6729acc29cb923516cb0d8f3478df62cea333aa12f019fa664","abstract_canon_sha256":"d50bfaf284ad6941ab9aa87f2c0f02753cbb3746f9d39eb41e226d69b027f481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:58.391838Z","signature_b64":"HEyKp/2LY1jjR5bVCJaMIjZ04Spn3nfbYp5bCUo5jdRTKx3D52HdXNkhC1ETMUGOiv175cDiez1ki9mKu33lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e5f7cd23d73afb1668c59fd49dc666be6a2b7a9d0d4594de0a76160313dd672","last_reissued_at":"2026-07-05T10:52:58.391348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:58.391348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Guoying Gu, Gu Zhang, Han Xue, Huazhe Xu, Jieji Ren, Wendi Chen, Yuan Fang","submitted_at":"2025-03-04T18:58:21Z","abstract_excerpt":"Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces; however, this remains challenging for robots. Existing visual imitation learning (IL) approaches rely on action chunking to model complex behaviors, which lacks the ability to respond instantly to real-time tactile feedback during the chunk execution. Furthermore, most teleoperation systems struggle to provide fine-grained tactile / force feedback, which limits the range of tasks that can be performed. To ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02881","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/2503.02881/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":"2503.02881","created_at":"2026-07-05T10:52:58.391408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02881v3","created_at":"2026-07-05T10:52:58.391408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02881","created_at":"2026-07-05T10:52:58.391408+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZPXZUR5OOX3","created_at":"2026-07-05T10:52:58.391408+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZPXZUR5OOX3CZUM","created_at":"2026-07-05T10:52:58.391408+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZPXZUR5","created_at":"2026-07-05T10:52:58.391408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.07287","citing_title":"TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07287","citing_title":"TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06262","citing_title":"Optimal Transport Q-Learning for Flow Policy Steering and Acceleration","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26663","citing_title":"Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13102","citing_title":"FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01684","citing_title":"Imagining the Sense of Touch: Touch-Informed Manipulation via Imagined Tactile Representations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12069","citing_title":"Tac-DINO: Learning Vision-Tactile Features with Patch Alignment","ref_index":178,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11184","citing_title":"TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10818","citing_title":"IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10862","citing_title":"LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08737","citing_title":"Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06281","citing_title":"Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31723","citing_title":"UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29941","citing_title":"Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25216","citing_title":"InvariantCloud: A Globally Invariant, Uniquely Indexed Point Cloud Framework for Robust 6-DoF Tactile Pose Tracking","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13618","citing_title":"On the Importance of Tactile Sensing for Imitation Learning: A Case Study on Robotic Match Lighting","ref_index":31,"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":42,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02738","citing_title":"Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04812","citing_title":"Multimodal Diffusion Forcing for Forceful Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17092","citing_title":"SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23864","citing_title":"Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05117","citing_title":"SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02600","citing_title":"CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21331","citing_title":"FingerViP: Learning Real-World Dexterous Manipulation with Fingertip Visual Perception","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP","json":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP.json","graph_json":"https://pith.science/api/pith-number/DZPXZUR5OOX3CZUMLH6UTXDGNP/graph.json","events_json":"https://pith.science/api/pith-number/DZPXZUR5OOX3CZUMLH6UTXDGNP/events.json","paper":"https://pith.science/paper/DZPXZUR5"},"agent_actions":{"view_html":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP","download_json":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP.json","view_paper":"https://pith.science/paper/DZPXZUR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02881&json=true","fetch_graph":"https://pith.science/api/pith-number/DZPXZUR5OOX3CZUMLH6UTXDGNP/graph.json","fetch_events":"https://pith.science/api/pith-number/DZPXZUR5OOX3CZUMLH6UTXDGNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP/action/storage_attestation","attest_author":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP/action/author_attestation","sign_citation":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP/action/citation_signature","submit_replication":"https://pith.science/pith/DZPXZUR5OOX3CZUMLH6UTXDGNP/action/replication_record"}},"created_at":"2026-07-05T10:52:58.391408+00:00","updated_at":"2026-07-05T10:52:58.391408+00:00"}