{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SPDPFBJWCSALPULZOVB4AFVLDV","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":"cfd650cc8abfa4fb901aa1cdbbe15e1b56f9dd2c3e40f0c761a41679604e30da","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:59:01Z","title_canon_sha256":"4d639d3a5892d45ffba995a55d1a01ea336279648c3b3029ccd98d3522c161db"},"schema_version":"1.0","source":{"id":"2210.03109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03109","created_at":"2026-07-05T05:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03109v1","created_at":"2026-07-05T05:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03109","created_at":"2026-07-05T05:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"SPDPFBJWCSAL","created_at":"2026-07-05T05:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"SPDPFBJWCSALPULZ","created_at":"2026-07-05T05:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"SPDPFBJW","created_at":"2026-07-05T05:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:eab37b494aee4dc6e09bc9f6c092df23febe8288afffde8697932ec58674a526","target":"graph","created_at":"2026-07-05T05:04:07Z","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/2210.03109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations are pre-trained via a masked autoencoder (MAE), frozen, and then passed into a learnable control module. Unlike prior work, we show that the pre-trained representations are effective across a range of real-world robotic tasks and embodiments. We find that our encoder consistently outperforms CLIP (up to 75%), supervised ImageNet pre-training (up to 81%), and training from scratch (up to 81%). Finally, we train a 307M p","authors_text":"Ilija Radosavovic, Jitendra Malik, Pieter Abbeel, Stephen James, Tete Xiao, Trevor Darrell","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:59:01Z","title":"Real-World Robot Learning with Masked Visual Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03109","kind":"arxiv","version":1},"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":"sha256:386f4d8e064c28eea22fb928fdcf9b48ef2dab20aba5d074fd75dc10d10e6ada","target":"record","created_at":"2026-07-05T05:04:07Z","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":"cfd650cc8abfa4fb901aa1cdbbe15e1b56f9dd2c3e40f0c761a41679604e30da","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:59:01Z","title_canon_sha256":"4d639d3a5892d45ffba995a55d1a01ea336279648c3b3029ccd98d3522c161db"},"schema_version":"1.0","source":{"id":"2210.03109","kind":"arxiv","version":1}},"canonical_sha256":"93c6f285361480b7d1797543c016ab1d5b48fe8f8875752b8fb9fcb21af4a5de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93c6f285361480b7d1797543c016ab1d5b48fe8f8875752b8fb9fcb21af4a5de","first_computed_at":"2026-07-05T05:04:07.710834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:07.710834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oaWToVEBKIPjHISbRACDQFtzPBpLPAKYvTBixDid6jrJh57XiBFLKLyuZTgg15ydab32cu+FQpuLG6ip46MSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:07.711307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:386f4d8e064c28eea22fb928fdcf9b48ef2dab20aba5d074fd75dc10d10e6ada","sha256:eab37b494aee4dc6e09bc9f6c092df23febe8288afffde8697932ec58674a526"],"state_sha256":"190fa08a88f0a1fa4f7c8c8edec86a0deee4a0caea7384f9765da1eb9720c16a"}