{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ODXYGA3M2KKQ6MN6QE3CYNONG4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4bd75ff9496d65b475fa8286e93662ad12a6f6f1b6689255348cd693461e2cc0","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-16T17:58:10Z","title_canon_sha256":"4227b307da034b948c2ad83f19651dc89e49d0d28945963e382bafb5a267b4cd"},"schema_version":"1.0","source":{"id":"2306.10007","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10007","created_at":"2026-07-05T07:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10007v2","created_at":"2026-07-05T07:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10007","created_at":"2026-07-05T07:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"ODXYGA3M2KKQ","created_at":"2026-07-05T07:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"ODXYGA3M2KKQ6MN6","created_at":"2026-07-05T07:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"ODXYGA3M","created_at":"2026-07-05T07:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:77424794ac8d116e2257fa0e958f637588e1072c168e72020db0713ecba46efb","target":"graph","created_at":"2026-07-05T07:23:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.10007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baifeng Shi, Ilija Radosavovic, Jitendra Malik, Ken Goldberg, Letian Fu, Trevor Darrell","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-16T17:58:10Z","title":"Robot Learning with Sensorimotor Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10007","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e999954705f1bf8827122883e9c68fb0746f55b7f052f6dd8de4ce5d256bdef","target":"record","created_at":"2026-07-05T07:23:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4bd75ff9496d65b475fa8286e93662ad12a6f6f1b6689255348cd693461e2cc0","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-16T17:58:10Z","title_canon_sha256":"4227b307da034b948c2ad83f19651dc89e49d0d28945963e382bafb5a267b4cd"},"schema_version":"1.0","source":{"id":"2306.10007","kind":"arxiv","version":2}},"canonical_sha256":"70ef83036cd2950f31be81362c35cd373ddf528b096cb97b33c08a21a20604a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70ef83036cd2950f31be81362c35cd373ddf528b096cb97b33c08a21a20604a2","first_computed_at":"2026-07-05T07:23:58.362333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:58.362333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHVVD21eCVpHLoZ0ItEDNKk1s37Ke9E/pWfEvviNelv/AFN20hG7HQ6RxNRmIrb91ew4crPAENOCeTeJnD7PBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:58.362775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10007","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e999954705f1bf8827122883e9c68fb0746f55b7f052f6dd8de4ce5d256bdef","sha256:77424794ac8d116e2257fa0e958f637588e1072c168e72020db0713ecba46efb"],"state_sha256":"2e58975cd313d0579fed96246e37835450196e7ba8c029cdf50d2fbdd562717f"}