{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DXPYVQJ6P7UGRWAG4O26GQUHAE","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":"893148407e58dac1118bd84b643bfb9803f3f060a4b2b15a6166a419c0ca9c90","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:26:14Z","title_canon_sha256":"6ddb1d9d42e24784de81763b8720af10d43a8ee36e366f469d29cce5a3177539"},"schema_version":"1.0","source":{"id":"2203.03580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.03580","created_at":"2026-07-05T04:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.03580v2","created_at":"2026-07-05T04:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03580","created_at":"2026-07-05T04:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"DXPYVQJ6P7UG","created_at":"2026-07-05T04:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"DXPYVQJ6P7UGRWAG","created_at":"2026-07-05T04:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"DXPYVQJ6","created_at":"2026-07-05T04:46:53Z"}],"graph_snapshots":[{"event_id":"sha256:aed2c3ea871725c63e434608d88ba410f3a3977046493b08c3da83138e81bf30","target":"graph","created_at":"2026-07-05T04:46:53Z","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/2203.03580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have seen the emergence of pre-trained representations as a powerful abstraction for AI applications in computer vision, natural language, and speech. However, policy learning for control is still dominated by a tabula-rasa learning paradigm, with visuo-motor policies often trained from scratch using data from deployment environments. In this context, we revisit and study the role of pre-trained visual representations for control, and in particular representations trained on large-scale computer vision datasets. Through extensive empirical evaluation in diverse control domains (Ha","authors_text":"Abhinav Gupta, Aravind Rajeswaran, Senthil Purushwalkam, Simone Parisi","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:26:14Z","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03580","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":"sha256:91a3bad9a2356781770b854621f6be98b11c7b08d934df2d94588c98a4501389","target":"record","created_at":"2026-07-05T04:46:53Z","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":"893148407e58dac1118bd84b643bfb9803f3f060a4b2b15a6166a419c0ca9c90","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:26:14Z","title_canon_sha256":"6ddb1d9d42e24784de81763b8720af10d43a8ee36e366f469d29cce5a3177539"},"schema_version":"1.0","source":{"id":"2203.03580","kind":"arxiv","version":2}},"canonical_sha256":"1ddf8ac13e7fe868d806e3b5e3428701285f2df887129b82562304b6d13b562b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ddf8ac13e7fe868d806e3b5e3428701285f2df887129b82562304b6d13b562b","first_computed_at":"2026-07-05T04:46:53.253470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:53.253470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IDX4MiTmcIcvY41w3BrwQpToMn+RM31CPTCY8oOo6rBYh9Ur+ff4swGZuR5KkTscC3Ju5dNqoGba5F9fHU2mDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:53.253922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.03580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91a3bad9a2356781770b854621f6be98b11c7b08d934df2d94588c98a4501389","sha256:aed2c3ea871725c63e434608d88ba410f3a3977046493b08c3da83138e81bf30"],"state_sha256":"5b344a7d10a1d02ea4f5731568258c7be9358570da7d38d43cf1ed68d74466cc"}