{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ECW4QGCZJK2W276W5QJGM55HCX","short_pith_number":"pith:ECW4QGCZ","schema_version":"1.0","canonical_sha256":"20adc818594ab56d7fd6ec126677a715ed12c5e17115bf449181eb566632db7e","source":{"kind":"arxiv","id":"2512.10946","version":2},"attestation_state":"computed","paper":{"title":"ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Chuan Wen, Fangyuan Zhou, Han Xue, Jun Lv, Shirun Tang, Wendi Chen, Yang Jin, Yi Wang","submitted_at":"2025-12-11T18:59:46Z","abstract_excerpt":"Human-level contact-rich manipulation relies on the distinct roles of two key modalities: vision provides spatially rich but temporally slow global context, while force sensing captures rapid local contact dynamics. Integrating these signals is challenging due to their fundamental frequency and informational disparities. In this work, we propose ImplicitRDP, a unified end-to-end visual-force diffusion policy that integrates visual planning and reactive force control within a single network. We introduce Structural Slow-Fast Learning, a mechanism utilizing causal attention to simultaneously pro"},"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":"2512.10946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-11T18:59:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2b9fecf9c031bc728b341f26a726547f06dc9372551f0b32b7afdb5ba912beb2","abstract_canon_sha256":"e109e0e81d453620ed1546a292f6fdd30f3b54248b4417a67a71d333dc43c609"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:22:16.996480Z","signature_b64":"8ZVehKxK4zMYjzoQMcx0c0sm32BdOt67Obxix/IjQKybb1PViUV5ChZlDBH05/lQoNt9xLItK5xBMqQ6n4NrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20adc818594ab56d7fd6ec126677a715ed12c5e17115bf449181eb566632db7e","last_reissued_at":"2026-07-22T01:22:16.995561Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:22:16.995561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Chuan Wen, Fangyuan Zhou, Han Xue, Jun Lv, Shirun Tang, Wendi Chen, Yang Jin, Yi Wang","submitted_at":"2025-12-11T18:59:46Z","abstract_excerpt":"Human-level contact-rich manipulation relies on the distinct roles of two key modalities: vision provides spatially rich but temporally slow global context, while force sensing captures rapid local contact dynamics. Integrating these signals is challenging due to their fundamental frequency and informational disparities. In this work, we propose ImplicitRDP, a unified end-to-end visual-force diffusion policy that integrates visual planning and reactive force control within a single network. We introduce Structural Slow-Fast Learning, a mechanism utilizing causal attention to simultaneously pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10946","kind":"arxiv","version":2},"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/2512.10946/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":"2512.10946","created_at":"2026-07-22T01:22:16.995998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.10946v2","created_at":"2026-07-22T01:22:16.995998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10946","created_at":"2026-07-22T01:22:16.995998+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECW4QGCZJK2W","created_at":"2026-07-22T01:22:16.995998+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECW4QGCZJK2W276W","created_at":"2026-07-22T01:22:16.995998+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECW4QGCZ","created_at":"2026-07-22T01:22:16.995998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.29941","citing_title":"Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13015","citing_title":"Learning Versatile Humanoid Manipulation with Touch Dreaming","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX","json":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX.json","graph_json":"https://pith.science/api/pith-number/ECW4QGCZJK2W276W5QJGM55HCX/graph.json","events_json":"https://pith.science/api/pith-number/ECW4QGCZJK2W276W5QJGM55HCX/events.json","paper":"https://pith.science/paper/ECW4QGCZ"},"agent_actions":{"view_html":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX","download_json":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX.json","view_paper":"https://pith.science/paper/ECW4QGCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.10946&json=true","fetch_graph":"https://pith.science/api/pith-number/ECW4QGCZJK2W276W5QJGM55HCX/graph.json","fetch_events":"https://pith.science/api/pith-number/ECW4QGCZJK2W276W5QJGM55HCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX/action/storage_attestation","attest_author":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX/action/author_attestation","sign_citation":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX/action/citation_signature","submit_replication":"https://pith.science/pith/ECW4QGCZJK2W276W5QJGM55HCX/action/replication_record"}},"created_at":"2026-07-22T01:22:16.995998+00:00","updated_at":"2026-07-22T01:22:16.995998+00:00"}