{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ODXYGA3M2KKQ6MN6QE3CYNONG4","short_pith_number":"pith:ODXYGA3M","schema_version":"1.0","canonical_sha256":"70ef83036cd2950f31be81362c35cd373ddf528b096cb97b33c08a21a20604a2","source":{"kind":"arxiv","id":"2306.10007","version":2},"attestation_state":"computed","paper":{"title":"Robot Learning with Sensorimotor Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Baifeng Shi, Ilija Radosavovic, Jitendra Malik, Ken Goldberg, Letian Fu, Trevor Darrell","submitted_at":"2023-06-16T17:58:10Z","abstract_excerpt":"We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive robot states, and actions, we encode the sequence into tokens, mask out a subset, and train a model to predict the missing content from the rest. We hypothesize that if a robot can predict the masked-out content it will have acquired a good model of the physical world that can enable it to act. RPT is designed to operate on latent visual representations which makes prediction tr"},"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":"2306.10007","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-16T17:58:10Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"4227b307da034b948c2ad83f19651dc89e49d0d28945963e382bafb5a267b4cd","abstract_canon_sha256":"4bd75ff9496d65b475fa8286e93662ad12a6f6f1b6689255348cd693461e2cc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:58.362775Z","signature_b64":"JHVVD21eCVpHLoZ0ItEDNKk1s37Ke9E/pWfEvviNelv/AFN20hG7HQ6RxNRmIrb91ew4crPAENOCeTeJnD7PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70ef83036cd2950f31be81362c35cd373ddf528b096cb97b33c08a21a20604a2","last_reissued_at":"2026-07-05T07:23:58.362333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:58.362333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Learning with Sensorimotor Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Baifeng Shi, Ilija Radosavovic, Jitendra Malik, Ken Goldberg, Letian Fu, Trevor Darrell","submitted_at":"2023-06-16T17:58:10Z","abstract_excerpt":"We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive robot states, and actions, we encode the sequence into tokens, mask out a subset, and train a model to predict the missing content from the rest. We hypothesize that if a robot can predict the masked-out content it will have acquired a good model of the physical world that can enable it to act. RPT is designed to operate on latent visual representations which makes prediction tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10007","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/2306.10007/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":"2306.10007","created_at":"2026-07-05T07:23:58.362390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10007v2","created_at":"2026-07-05T07:23:58.362390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10007","created_at":"2026-07-05T07:23:58.362390+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODXYGA3M2KKQ","created_at":"2026-07-05T07:23:58.362390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODXYGA3M2KKQ6MN6","created_at":"2026-07-05T07:23:58.362390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODXYGA3M","created_at":"2026-07-05T07:23:58.362390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.02115","citing_title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02117","citing_title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4","json":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4.json","graph_json":"https://pith.science/api/pith-number/ODXYGA3M2KKQ6MN6QE3CYNONG4/graph.json","events_json":"https://pith.science/api/pith-number/ODXYGA3M2KKQ6MN6QE3CYNONG4/events.json","paper":"https://pith.science/paper/ODXYGA3M"},"agent_actions":{"view_html":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4","download_json":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4.json","view_paper":"https://pith.science/paper/ODXYGA3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10007&json=true","fetch_graph":"https://pith.science/api/pith-number/ODXYGA3M2KKQ6MN6QE3CYNONG4/graph.json","fetch_events":"https://pith.science/api/pith-number/ODXYGA3M2KKQ6MN6QE3CYNONG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4/action/storage_attestation","attest_author":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4/action/author_attestation","sign_citation":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4/action/citation_signature","submit_replication":"https://pith.science/pith/ODXYGA3M2KKQ6MN6QE3CYNONG4/action/replication_record"}},"created_at":"2026-07-05T07:23:58.362390+00:00","updated_at":"2026-07-05T07:23:58.362390+00:00"}