{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OLCSPJANLI3SBEDYBXCGIHIPUO","short_pith_number":"pith:OLCSPJAN","schema_version":"1.0","canonical_sha256":"72c527a40d5a372090780dc4641d0fa399032be3e1cfd9e8245b801407743a69","source":{"kind":"arxiv","id":"2210.10047","version":3},"attestation_state":"computed","paper":{"title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Nur Muhammad Mahi Shafiullah, Yibin Wang, Zichen Jeff Cui","submitted_at":"2022-10-18T17:59:55Z","abstract_excerpt":"While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the"},"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":"2210.10047","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-18T17:59:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"716fa79d9bc67d6f8ed74ec593f9d0d815d455d3dc5659afb05ca67084e1c1bb","abstract_canon_sha256":"c4e7a57809ff825fc794d57f6cc7ca925de4804edf660fd1eec45f1fcbec608c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:51.260990Z","signature_b64":"v3Q2mFZMw/HxiaTRxt4kQlYAOirbVcQUujDVzg6EWktt27gBrrWZWBFhLH6uCEuVyCr5rdOUDtpGh39937jjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c527a40d5a372090780dc4641d0fa399032be3e1cfd9e8245b801407743a69","last_reissued_at":"2026-07-05T05:25:51.260509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:51.260509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Nur Muhammad Mahi Shafiullah, Yibin Wang, Zichen Jeff Cui","submitted_at":"2022-10-18T17:59:55Z","abstract_excerpt":"While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10047","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/2210.10047/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":"2210.10047","created_at":"2026-07-05T05:25:51.260566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10047v3","created_at":"2026-07-05T05:25:51.260566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10047","created_at":"2026-07-05T05:25:51.260566+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLCSPJANLI3S","created_at":"2026-07-05T05:25:51.260566+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLCSPJANLI3SBEDY","created_at":"2026-07-05T05:25:51.260566+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLCSPJAN","created_at":"2026-07-05T05:25:51.260566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23685","citing_title":"LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25813","citing_title":"Extending Embodied Question Answering from Perception to Decision","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23682","citing_title":"villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10126","citing_title":"AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02117","citing_title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13403","citing_title":"RotVLA: Rotational Latent Action for Vision-Language-Action Model","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06111","citing_title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19650","citing_title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05544","citing_title":"Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09246","citing_title":"OpenVLA: An Open-Source Vision-Language-Action Model","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO","json":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO.json","graph_json":"https://pith.science/api/pith-number/OLCSPJANLI3SBEDYBXCGIHIPUO/graph.json","events_json":"https://pith.science/api/pith-number/OLCSPJANLI3SBEDYBXCGIHIPUO/events.json","paper":"https://pith.science/paper/OLCSPJAN"},"agent_actions":{"view_html":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO","download_json":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO.json","view_paper":"https://pith.science/paper/OLCSPJAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10047&json=true","fetch_graph":"https://pith.science/api/pith-number/OLCSPJANLI3SBEDYBXCGIHIPUO/graph.json","fetch_events":"https://pith.science/api/pith-number/OLCSPJANLI3SBEDYBXCGIHIPUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO/action/storage_attestation","attest_author":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO/action/author_attestation","sign_citation":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO/action/citation_signature","submit_replication":"https://pith.science/pith/OLCSPJANLI3SBEDYBXCGIHIPUO/action/replication_record"}},"created_at":"2026-07-05T05:25:51.260566+00:00","updated_at":"2026-07-05T05:25:51.260566+00:00"}