{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OKOR4U24DNNRYPECHQIRQQYIU6","short_pith_number":"pith:OKOR4U24","schema_version":"1.0","canonical_sha256":"729d1e535c1b5b1c3c823c11184308a7987e044826dc42b5cb220a55c8a8fb7d","source":{"kind":"arxiv","id":"1812.11971","version":3},"attestation_state":"computed","paper":{"title":"Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Amir R. Zamir, Bradley Emi, Jitendra Malik, Leonidas Guibas, Silvio Savarese","submitted_at":"2018-12-31T18:59:25Z","abstract_excerpt":"How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set (e.g. a distance estimator, an edge detector, etc.) within a reinforcement learning framework--see Figure 1. This skill set (hereafter mid-level perception) provides the policy with a more processed state of the world compared to raw images.\n  We find that using a mid-level perception confers significant advantages over training end-to-end from scratch (i.e. "},"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":"1812.11971","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-31T18:59:25Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"e7e0d9e99eac125a9975f0eedce0e561dfcace40b9f3755148ada2fe2eca8e78","abstract_canon_sha256":"2ed18c3dc28fc6ca6e86a21d3e40d43d63680d858e2ae2a62b30fab0b9cf9ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.241709Z","signature_b64":"LiVDU9i0Mu+5mPqWfSqEDkkeemEU1Sind8nwZ6EMoJcWAge5O4IGsVT32Mlbmw4RDr5DfB/92GMY3rR54PCbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729d1e535c1b5b1c3c823c11184308a7987e044826dc42b5cb220a55c8a8fb7d","last_reissued_at":"2026-05-17T23:48:06.241261Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.241261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Amir R. Zamir, Bradley Emi, Jitendra Malik, Leonidas Guibas, Silvio Savarese","submitted_at":"2018-12-31T18:59:25Z","abstract_excerpt":"How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set (e.g. a distance estimator, an edge detector, etc.) within a reinforcement learning framework--see Figure 1. This skill set (hereafter mid-level perception) provides the policy with a more processed state of the world compared to raw images.\n  We find that using a mid-level perception confers significant advantages over training end-to-end from scratch (i.e. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11971","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.11971","created_at":"2026-05-17T23:48:06.241349+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11971v3","created_at":"2026-05-17T23:48:06.241349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11971","created_at":"2026-05-17T23:48:06.241349+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKOR4U24DNNR","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKOR4U24DNNRYPEC","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKOR4U24","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6","json":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6.json","graph_json":"https://pith.science/api/pith-number/OKOR4U24DNNRYPECHQIRQQYIU6/graph.json","events_json":"https://pith.science/api/pith-number/OKOR4U24DNNRYPECHQIRQQYIU6/events.json","paper":"https://pith.science/paper/OKOR4U24"},"agent_actions":{"view_html":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6","download_json":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6.json","view_paper":"https://pith.science/paper/OKOR4U24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11971&json=true","fetch_graph":"https://pith.science/api/pith-number/OKOR4U24DNNRYPECHQIRQQYIU6/graph.json","fetch_events":"https://pith.science/api/pith-number/OKOR4U24DNNRYPECHQIRQQYIU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6/action/storage_attestation","attest_author":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6/action/author_attestation","sign_citation":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6/action/citation_signature","submit_replication":"https://pith.science/pith/OKOR4U24DNNRYPECHQIRQQYIU6/action/replication_record"}},"created_at":"2026-05-17T23:48:06.241349+00:00","updated_at":"2026-05-17T23:48:06.241349+00:00"}