{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EWVK3MRV447BBUTJVV2MRHEN3R","short_pith_number":"pith:EWVK3MRV","schema_version":"1.0","canonical_sha256":"25aaadb235e73e10d269ad74c89c8ddc7dc8ce74e5d515c4611ea8c275fe5cf6","source":{"kind":"arxiv","id":"2210.00121","version":1},"attestation_state":"computed","paper":{"title":"Visuo-Tactile Transformers for Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Sipos, Mark Van der Merwe, Nima Fazeli, Yizhou Chen","submitted_at":"2022-09-30T22:38:29Z","abstract_excerpt":"Learning representations in the joint domain of vision and touch can improve manipulation dexterity, robustness, and sample-complexity by exploiting mutual information and complementary cues. Here, we present Visuo-Tactile Transformers (VTTs), a novel multimodal representation learning approach suited for model-based reinforcement learning and planning. Our approach extends the Visual Transformer \\cite{dosovitskiy2021image} to handle visuo-tactile feedback. Specifically, VTT uses tactile feedback together with self and cross-modal attention to build latent heatmap representations that focus at"},"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":"2210.00121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-30T22:38:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0795d41b81b6c90009fd9b776afebb2e5a5e6af99089e22a7fea63edd9932db5","abstract_canon_sha256":"54a192c20d82863e8c6c742901c8b47242d01736d3f0e344111c03c5e699e000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:28.758414Z","signature_b64":"lmJKaXpDPXPU5xFIQ3EJ/eHvHLmbsssLMfJpzMQpdeNNuWDP4HAMi1oiOM6N14rUacF4t264mtArnPoFhZiUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25aaadb235e73e10d269ad74c89c8ddc7dc8ce74e5d515c4611ea8c275fe5cf6","last_reissued_at":"2026-07-05T05:02:28.757969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:28.757969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visuo-Tactile Transformers for Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Sipos, Mark Van der Merwe, Nima Fazeli, Yizhou Chen","submitted_at":"2022-09-30T22:38:29Z","abstract_excerpt":"Learning representations in the joint domain of vision and touch can improve manipulation dexterity, robustness, and sample-complexity by exploiting mutual information and complementary cues. Here, we present Visuo-Tactile Transformers (VTTs), a novel multimodal representation learning approach suited for model-based reinforcement learning and planning. Our approach extends the Visual Transformer \\cite{dosovitskiy2021image} to handle visuo-tactile feedback. Specifically, VTT uses tactile feedback together with self and cross-modal attention to build latent heatmap representations that focus at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00121","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/2210.00121/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":"2210.00121","created_at":"2026-07-05T05:02:28.758023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00121v1","created_at":"2026-07-05T05:02:28.758023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00121","created_at":"2026-07-05T05:02:28.758023+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWVK3MRV447B","created_at":"2026-07-05T05:02:28.758023+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWVK3MRV447BBUTJ","created_at":"2026-07-05T05:02:28.758023+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWVK3MRV","created_at":"2026-07-05T05:02:28.758023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17336","citing_title":"Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R","json":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R.json","graph_json":"https://pith.science/api/pith-number/EWVK3MRV447BBUTJVV2MRHEN3R/graph.json","events_json":"https://pith.science/api/pith-number/EWVK3MRV447BBUTJVV2MRHEN3R/events.json","paper":"https://pith.science/paper/EWVK3MRV"},"agent_actions":{"view_html":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R","download_json":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R.json","view_paper":"https://pith.science/paper/EWVK3MRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00121&json=true","fetch_graph":"https://pith.science/api/pith-number/EWVK3MRV447BBUTJVV2MRHEN3R/graph.json","fetch_events":"https://pith.science/api/pith-number/EWVK3MRV447BBUTJVV2MRHEN3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R/action/storage_attestation","attest_author":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R/action/author_attestation","sign_citation":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R/action/citation_signature","submit_replication":"https://pith.science/pith/EWVK3MRV447BBUTJVV2MRHEN3R/action/replication_record"}},"created_at":"2026-07-05T05:02:28.758023+00:00","updated_at":"2026-07-05T05:02:28.758023+00:00"}