{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CWLPWADWTAUB6F3YT4XPLIC3UC","short_pith_number":"pith:CWLPWADW","schema_version":"1.0","canonical_sha256":"1596fb007698281f17789f2ef5a05ba0a17345bdaeb0323184cc97953654f3a4","source":{"kind":"arxiv","id":"2309.10175","version":1},"attestation_state":"computed","paper":{"title":"One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abraham George, Amir Barati Farimani","submitted_at":"2023-09-18T21:50:26Z","abstract_excerpt":"Learning from human demonstrations (behavior cloning) is a cornerstone of robot learning. However, most behavior cloning algorithms require a large number of demonstrations to learn a task, especially for general tasks that have a large variety of initial conditions. Humans, however, can learn to complete tasks, even complex ones, after only seeing one or two demonstrations. Our work seeks to emulate this ability, using behavior cloning to learn a task given only a single human demonstration. We achieve this goal by using linear transforms to augment the single demonstration, generating a set "},"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":"2309.10175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-18T21:50:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f971544ea6b306f79c130687e957a03ce6acc5a6e061a0d9fdbc4453236e1b57","abstract_canon_sha256":"317f3a8ab100bd19d75fe9afab2aa231a17210cb7b01a46f6eab32ab48794759"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:08.940219Z","signature_b64":"7RTVQOBHG3EkVhm1Bhw3nS1F4Bxh4lo3v6zgIjKAKdTi/JHIjCO2QXteWsPeJD+d6W8R2yGIFBlI+DTLkBlEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1596fb007698281f17789f2ef5a05ba0a17345bdaeb0323184cc97953654f3a4","last_reissued_at":"2026-07-05T06:52:08.939649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:08.939649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abraham George, Amir Barati Farimani","submitted_at":"2023-09-18T21:50:26Z","abstract_excerpt":"Learning from human demonstrations (behavior cloning) is a cornerstone of robot learning. However, most behavior cloning algorithms require a large number of demonstrations to learn a task, especially for general tasks that have a large variety of initial conditions. Humans, however, can learn to complete tasks, even complex ones, after only seeing one or two demonstrations. Our work seeks to emulate this ability, using behavior cloning to learn a task given only a single human demonstration. We achieve this goal by using linear transforms to augment the single demonstration, generating a set "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10175","kind":"arxiv","version":1},"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/2309.10175/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":"2309.10175","created_at":"2026-07-05T06:52:08.939715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10175v1","created_at":"2026-07-05T06:52:08.939715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10175","created_at":"2026-07-05T06:52:08.939715+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWLPWADWTAUB","created_at":"2026-07-05T06:52:08.939715+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWLPWADWTAUB6F3Y","created_at":"2026-07-05T06:52:08.939715+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWLPWADW","created_at":"2026-07-05T06:52:08.939715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02448","citing_title":"AgentsCAD: Automated Design for Manufacturing of FDM Parts via Multi-Agent LLM Reasoning and Geometric Feature Recognition","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27114","citing_title":"VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07969","citing_title":"Reinforcement Learning with Action Chunking","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25241","citing_title":"One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07339","citing_title":"Real-Time Execution of Action Chunking Flow Policies","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC","json":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC.json","graph_json":"https://pith.science/api/pith-number/CWLPWADWTAUB6F3YT4XPLIC3UC/graph.json","events_json":"https://pith.science/api/pith-number/CWLPWADWTAUB6F3YT4XPLIC3UC/events.json","paper":"https://pith.science/paper/CWLPWADW"},"agent_actions":{"view_html":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC","download_json":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC.json","view_paper":"https://pith.science/paper/CWLPWADW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10175&json=true","fetch_graph":"https://pith.science/api/pith-number/CWLPWADWTAUB6F3YT4XPLIC3UC/graph.json","fetch_events":"https://pith.science/api/pith-number/CWLPWADWTAUB6F3YT4XPLIC3UC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC/action/storage_attestation","attest_author":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC/action/author_attestation","sign_citation":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC/action/citation_signature","submit_replication":"https://pith.science/pith/CWLPWADWTAUB6F3YT4XPLIC3UC/action/replication_record"}},"created_at":"2026-07-05T06:52:08.939715+00:00","updated_at":"2026-07-05T06:52:08.939715+00:00"}