{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WQ55W4A7LUSBDLDOS7BOYTV5R4","short_pith_number":"pith:WQ55W4A7","schema_version":"1.0","canonical_sha256":"b43bdb701f5d2411ac6e97c2ec4ebd8f07fce0cffbd6c9e085436ab5752ee940","source":{"kind":"arxiv","id":"2211.12498","version":2},"attestation_state":"computed","paper":{"title":"Touch and Go: Learning from Human-Collected Vision and Touch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Chenyang Ma, Fengyu Yang, Jiacheng Zhang, Jing Zhu, Wenzhen Yuan","submitted_at":"2022-11-22T18:59:32Z","abstract_excerpt":"The ability to associate touch with sight is essential for tasks that require physically interacting with objects in the world. We propose a dataset with paired visual and tactile data called Touch and Go, in which human data collectors probe objects in natural environments using tactile sensors, while simultaneously recording egocentric video. In contrast to previous efforts, which have largely been confined to lab settings or simulated environments, our dataset spans a large number of \"in the wild\" objects and scenes. To demonstrate our dataset's effectiveness, we successfully apply it to a "},"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":"2211.12498","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T18:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"70e7ca894f6cf1563b793e62d76e80a9ac98f57c40d452bcc7242b49f56b8c63","abstract_canon_sha256":"5697ca1628eeb4cb1955305881d089e670caabcb838b858f2df8023a90101150"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:16.236694Z","signature_b64":"dCxahXnY4c9lY6dYxABDBRF1wkjdk+118YS8isILO8RnHB23aECvXDH3EPzkFJoGlZT5+cukBdygKGrJhLshBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43bdb701f5d2411ac6e97c2ec4ebd8f07fce0cffbd6c9e085436ab5752ee940","last_reissued_at":"2026-07-05T05:20:16.236282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:16.236282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Touch and Go: Learning from Human-Collected Vision and Touch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Chenyang Ma, Fengyu Yang, Jiacheng Zhang, Jing Zhu, Wenzhen Yuan","submitted_at":"2022-11-22T18:59:32Z","abstract_excerpt":"The ability to associate touch with sight is essential for tasks that require physically interacting with objects in the world. We propose a dataset with paired visual and tactile data called Touch and Go, in which human data collectors probe objects in natural environments using tactile sensors, while simultaneously recording egocentric video. In contrast to previous efforts, which have largely been confined to lab settings or simulated environments, our dataset spans a large number of \"in the wild\" objects and scenes. To demonstrate our dataset's effectiveness, we successfully apply it to a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12498","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/2211.12498/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":"2211.12498","created_at":"2026-07-05T05:20:16.236341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12498v2","created_at":"2026-07-05T05:20:16.236341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12498","created_at":"2026-07-05T05:20:16.236341+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ55W4A7LUSB","created_at":"2026-07-05T05:20:16.236341+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ55W4A7LUSBDLDO","created_at":"2026-07-05T05:20:16.236341+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ55W4A7","created_at":"2026-07-05T05:20:16.236341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11743","citing_title":"TacCoRL: Integrating Tactile Feedback into VLA via Simulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11637","citing_title":"TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12069","citing_title":"Tac-DINO: Learning Vision-Tactile Features with Patch Alignment","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04825","citing_title":"HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31451","citing_title":"UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29948","citing_title":"Heterogeneous Tactile Transformer","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27154","citing_title":"Touch-R1: Reinforcing Touch Reasoning in MLLMs","ref_index":30,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13848","citing_title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4","json":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4.json","graph_json":"https://pith.science/api/pith-number/WQ55W4A7LUSBDLDOS7BOYTV5R4/graph.json","events_json":"https://pith.science/api/pith-number/WQ55W4A7LUSBDLDOS7BOYTV5R4/events.json","paper":"https://pith.science/paper/WQ55W4A7"},"agent_actions":{"view_html":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4","download_json":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4.json","view_paper":"https://pith.science/paper/WQ55W4A7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12498&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ55W4A7LUSBDLDOS7BOYTV5R4/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ55W4A7LUSBDLDOS7BOYTV5R4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4/action/storage_attestation","attest_author":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4/action/author_attestation","sign_citation":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4/action/citation_signature","submit_replication":"https://pith.science/pith/WQ55W4A7LUSBDLDOS7BOYTV5R4/action/replication_record"}},"created_at":"2026-07-05T05:20:16.236341+00:00","updated_at":"2026-07-05T05:20:16.236341+00:00"}