{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:W5TG7NBXY6WDT34SJCWG2WED6L","short_pith_number":"pith:W5TG7NBX","schema_version":"1.0","canonical_sha256":"b7666fb437c7ac39ef9248ac6d5883f2ff19434b01a743b497cc0c51aa49ba7c","source":{"kind":"arxiv","id":"2012.07975","version":3},"attestation_state":"computed","paper":{"title":"Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Albert Zhan, Lerrel Pinto, Michael Laskin, Pieter Abbeel, Ruihan Zhao","submitted_at":"2020-12-14T22:18:39Z","abstract_excerpt":"Recent advances in unsupervised representation learning significantly improved the sample efficiency of training Reinforcement Learning policies in simulated environments. However, similar gains have not yet been seen for real-robot reinforcement learning. In this work, we focus on enabling data-efficient real-robot learning from pixels. We present Contrastive Pre-training and Data Augmentation for Efficient Robotic Learning (CoDER), a method that utilizes data augmentation and unsupervised learning to achieve sample-efficient training of real-robot arm policies from sparse rewards. While cont"},"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":"2012.07975","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2020-12-14T22:18:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"92c480a5f846e9866d89d7b2789e7799346bfbf3d91adb6868c98728842f8d6e","abstract_canon_sha256":"d9c8ff9988974e863373bf5f51d49d24d0249cc6055512b9cdc701abed006d0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:49.706806Z","signature_b64":"TD112sgVOc7ogewLr2Y9ffQxlMNJfpETqxNkvZ8X1Kf6L+Y8RdOC6+wp/9BQZzSAV5cmUHV+J0RjBCN9h6PGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7666fb437c7ac39ef9248ac6d5883f2ff19434b01a743b497cc0c51aa49ba7c","last_reissued_at":"2026-07-05T05:06:49.706382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:49.706382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Albert Zhan, Lerrel Pinto, Michael Laskin, Pieter Abbeel, Ruihan Zhao","submitted_at":"2020-12-14T22:18:39Z","abstract_excerpt":"Recent advances in unsupervised representation learning significantly improved the sample efficiency of training Reinforcement Learning policies in simulated environments. However, similar gains have not yet been seen for real-robot reinforcement learning. In this work, we focus on enabling data-efficient real-robot learning from pixels. We present Contrastive Pre-training and Data Augmentation for Efficient Robotic Learning (CoDER), a method that utilizes data augmentation and unsupervised learning to achieve sample-efficient training of real-robot arm policies from sparse rewards. While cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07975","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.07975/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":"2012.07975","created_at":"2026-07-05T05:06:49.706439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07975v3","created_at":"2026-07-05T05:06:49.706439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07975","created_at":"2026-07-05T05:06:49.706439+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5TG7NBXY6WD","created_at":"2026-07-05T05:06:49.706439+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5TG7NBXY6WDT34S","created_at":"2026-07-05T05:06:49.706439+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5TG7NBX","created_at":"2026-07-05T05:06:49.706439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L","json":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L.json","graph_json":"https://pith.science/api/pith-number/W5TG7NBXY6WDT34SJCWG2WED6L/graph.json","events_json":"https://pith.science/api/pith-number/W5TG7NBXY6WDT34SJCWG2WED6L/events.json","paper":"https://pith.science/paper/W5TG7NBX"},"agent_actions":{"view_html":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L","download_json":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L.json","view_paper":"https://pith.science/paper/W5TG7NBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07975&json=true","fetch_graph":"https://pith.science/api/pith-number/W5TG7NBXY6WDT34SJCWG2WED6L/graph.json","fetch_events":"https://pith.science/api/pith-number/W5TG7NBXY6WDT34SJCWG2WED6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L/action/storage_attestation","attest_author":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L/action/author_attestation","sign_citation":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L/action/citation_signature","submit_replication":"https://pith.science/pith/W5TG7NBXY6WDT34SJCWG2WED6L/action/replication_record"}},"created_at":"2026-07-05T05:06:49.706439+00:00","updated_at":"2026-07-05T05:06:49.706439+00:00"}