{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S3SKIEJBIS3HAUCBY3H2BXXSJN","short_pith_number":"pith:S3SKIEJB","schema_version":"1.0","canonical_sha256":"96e4a4112144b6705041c6cfa0def24b66a6cccc802548f7ea25aadd58f649e3","source":{"kind":"arxiv","id":"2210.05178","version":3},"attestation_state":"computed","paper":{"title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Anikait Singh, Aviral Kumar, Chelsea Finn, Frederik Ebert, Mitsuhiko Nakamoto, Sergey Levine, Yanlai Yang","submitted_at":"2022-10-11T06:30:53Z","abstract_excerpt":"Progress in deep learning highlights the tremendous potential of utilizing diverse robotic datasets for attaining effective generalization and makes it enticing to consider leveraging broad datasets for attaining robust generalization in robotic learning as well. However, in practice, we often want to learn a new skill in a new environment that is unlikely to be contained in the prior data. Therefore we ask: how can we leverage existing diverse offline datasets in combination with small amounts of task-specific data to solve new tasks, while still enjoying the generalization benefits of traini"},"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":"2210.05178","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2022-10-11T06:30:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"05c3d757467f5164a10750e76f30a8d241d5d761e3df67ab4a535346f0adbd64","abstract_canon_sha256":"fee70eec65f7d3bea70c16b23773f6bfb593e122a2e410f0e5d6f7691a1a914d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:31.784594Z","signature_b64":"THj4zvBG2wWC1aBRDozhjZg8d2DonIbawSbJy2Pb+802ckg0+wGel3EiZwKuMfuyxzpXg5yif26wEd5oMZ61Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96e4a4112144b6705041c6cfa0def24b66a6cccc802548f7ea25aadd58f649e3","last_reissued_at":"2026-07-05T06:53:31.784119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:31.784119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Anikait Singh, Aviral Kumar, Chelsea Finn, Frederik Ebert, Mitsuhiko Nakamoto, Sergey Levine, Yanlai Yang","submitted_at":"2022-10-11T06:30:53Z","abstract_excerpt":"Progress in deep learning highlights the tremendous potential of utilizing diverse robotic datasets for attaining effective generalization and makes it enticing to consider leveraging broad datasets for attaining robust generalization in robotic learning as well. However, in practice, we often want to learn a new skill in a new environment that is unlikely to be contained in the prior data. Therefore we ask: how can we leverage existing diverse offline datasets in combination with small amounts of task-specific data to solve new tasks, while still enjoying the generalization benefits of traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05178","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/2210.05178/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":"2210.05178","created_at":"2026-07-05T06:53:31.784192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05178v3","created_at":"2026-07-05T06:53:31.784192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05178","created_at":"2026-07-05T06:53:31.784192+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3SKIEJBIS3H","created_at":"2026-07-05T06:53:31.784192+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3SKIEJBIS3HAUCB","created_at":"2026-07-05T06:53:31.784192+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3SKIEJB","created_at":"2026-07-05T06:53:31.784192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.07399","citing_title":"VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22376","citing_title":"Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12514","citing_title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02523","citing_title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN","json":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN.json","graph_json":"https://pith.science/api/pith-number/S3SKIEJBIS3HAUCBY3H2BXXSJN/graph.json","events_json":"https://pith.science/api/pith-number/S3SKIEJBIS3HAUCBY3H2BXXSJN/events.json","paper":"https://pith.science/paper/S3SKIEJB"},"agent_actions":{"view_html":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN","download_json":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN.json","view_paper":"https://pith.science/paper/S3SKIEJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05178&json=true","fetch_graph":"https://pith.science/api/pith-number/S3SKIEJBIS3HAUCBY3H2BXXSJN/graph.json","fetch_events":"https://pith.science/api/pith-number/S3SKIEJBIS3HAUCBY3H2BXXSJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN/action/storage_attestation","attest_author":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN/action/author_attestation","sign_citation":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN/action/citation_signature","submit_replication":"https://pith.science/pith/S3SKIEJBIS3HAUCBY3H2BXXSJN/action/replication_record"}},"created_at":"2026-07-05T06:53:31.784192+00:00","updated_at":"2026-07-05T06:53:31.784192+00:00"}