{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2GGKXCCPWRQOGGJMT2E2IZRBM3","short_pith_number":"pith:2GGKXCCP","schema_version":"1.0","canonical_sha256":"d18cab884fb460e3192c9e89a4662166da4e59e7623943866e11aa458afe9cbe","source":{"kind":"arxiv","id":"2310.17596","version":1},"attestation_state":"computed","paper":{"title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MimicGen adapts a few hundred human demonstrations into over 50,000 varied examples that train robots for long-horizon tasks.","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Bowen Wen, Dieter Fox, Iretiayo Akinola, Linxi Fan, Soroush Nasiriany, Yashraj Narang, Yuke Zhu","submitted_at":"2023-10-26T17:17:31Z","abstract_excerpt":"Imitation learning from a large set of human demonstrations has proved to be an effective paradigm for building capable robot agents. However, the demonstrations can be extremely costly and time-consuming to collect. We introduce MimicGen, a system for automatically synthesizing large-scale, rich datasets from only a small number of human demonstrations by adapting them to new contexts. We use MimicGen to generate over 50K demonstrations across 18 tasks with diverse scene configurations, object instances, and robot arms from just ~200 human demonstrations. We show that robot agents can be effe"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2310.17596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-26T17:17:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d6fea5c706970428a6d8f92ede1082cd04b4b97d4b827f9d10cd54bf0974c18c","abstract_canon_sha256":"fd32293c87e7979d28a0e23cc75e24514c9db5ae8865198c675dfb4480fbea40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.464197Z","signature_b64":"nD9a6yLU8BTKMI5FUA14qWZnZ3zY1LKkUAeRrF31Xvd+bajzXyGAHJcSVjjd7pjnF4lHCHO+I5OZM53qbit+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d18cab884fb460e3192c9e89a4662166da4e59e7623943866e11aa458afe9cbe","last_reissued_at":"2026-05-17T23:38:14.463497Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.463497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MimicGen adapts a few hundred human demonstrations into over 50,000 varied examples that train robots for long-horizon tasks.","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Bowen Wen, Dieter Fox, Iretiayo Akinola, Linxi Fan, Soroush Nasiriany, Yashraj Narang, Yuke Zhu","submitted_at":"2023-10-26T17:17:31Z","abstract_excerpt":"Imitation learning from a large set of human demonstrations has proved to be an effective paradigm for building capable robot agents. However, the demonstrations can be extremely costly and time-consuming to collect. We introduce MimicGen, a system for automatically synthesizing large-scale, rich datasets from only a small number of human demonstrations by adapting them to new contexts. We use MimicGen to generate over 50K demonstrations across 18 tasks with diverse scene configurations, object instances, and robot arms from just ~200 human demonstrations. We show that robot agents can be effe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that robot agents can be effectively trained on this generated dataset by imitation learning to achieve strong performance in long-horizon and high-precision tasks, such as multi-part assembly and coffee preparation, across broad initial state distributions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Adapting human demonstrations to new contexts produces data that is as effective for training as real human demonstrations collected in those contexts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MimicGen adapts a few hundred human demonstrations into over 50,000 varied examples that train robots for long-horizon tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d86744b0cfe07160d252e47089cfcc719f9e5b88e63e78c584a7a8c6c39c6ab8"},"source":{"id":"2310.17596","kind":"arxiv","version":1},"verdict":{"id":"c47a1c43-0807-4dcc-bfa0-9d2598d7cae5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T09:41:01.720309Z","strongest_claim":"We show that robot agents can be effectively trained on this generated dataset by imitation learning to achieve strong performance in long-horizon and high-precision tasks, such as multi-part assembly and coffee preparation, across broad initial state distributions.","one_line_summary":"MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Adapting human demonstrations to new contexts produces data that is as effective for training as real human demonstrations collected in those contexts.","pith_extraction_headline":"MimicGen adapts a few hundred human demonstrations into over 50,000 varied examples that train robots for long-horizon tasks."},"references":{"count":128,"sample":[{"doi":"","year":2017,"title":"Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation","work_id":"09d7abfe-a94e-47ef-8064-2329faccb197","ref_index":1,"cited_arxiv_id":"1710.04615","is_internal_anchor":true},{"doi":"","year":2018,"title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation,","work_id":"1f0e1f61-6910-4924-8f48-93cc372a3dc2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Bc- z: Zero-shot task generalization with robotic imitation learning,","work_id":"fd91f703-9aa1-495a-951b-403bced21c97","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":4,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":2022,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","ref_index":5,"cited_arxiv_id":"2212.06817","is_internal_anchor":true}],"resolved_work":128,"snapshot_sha256":"7ccca6e98ac266610acdb424a6d4be467ef44a4d81890659e227381e511e340a","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"91573c6ce45c5cc0765f91da94fed9634d7cee69b60a404aa32c65824f58d38e"},"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":"2310.17596","created_at":"2026-05-17T23:38:14.463618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17596v1","created_at":"2026-05-17T23:38:14.463618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17596","created_at":"2026-05-17T23:38:14.463618+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GGKXCCPWRQO","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GGKXCCPWRQOGGJM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GGKXCCP","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2507.07986","citing_title":"EXPO: Stable Reinforcement Learning with Expressive Policies","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.08547","citing_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2510.17640","citing_title":"RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2505.03233","citing_title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15956","citing_title":"ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":163,"is_internal_anchor":true},{"citing_arxiv_id":"2406.02523","citing_title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16163","citing_title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01529","citing_title":"Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01529","citing_title":"Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00244","citing_title":"Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18000","citing_title":"Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08664","citing_title":"Generative Simulation for Policy Learning in Physical Human-Robot Interaction","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08544","citing_title":"SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05544","citing_title":"Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13800","citing_title":"EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2410.24164","citing_title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13645","citing_title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15023","citing_title":"DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3","json":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3.json","graph_json":"https://pith.science/api/pith-number/2GGKXCCPWRQOGGJMT2E2IZRBM3/graph.json","events_json":"https://pith.science/api/pith-number/2GGKXCCPWRQOGGJMT2E2IZRBM3/events.json","paper":"https://pith.science/paper/2GGKXCCP"},"agent_actions":{"view_html":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3","download_json":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3.json","view_paper":"https://pith.science/paper/2GGKXCCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17596&json=true","fetch_graph":"https://pith.science/api/pith-number/2GGKXCCPWRQOGGJMT2E2IZRBM3/graph.json","fetch_events":"https://pith.science/api/pith-number/2GGKXCCPWRQOGGJMT2E2IZRBM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3/action/storage_attestation","attest_author":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3/action/author_attestation","sign_citation":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3/action/citation_signature","submit_replication":"https://pith.science/pith/2GGKXCCPWRQOGGJMT2E2IZRBM3/action/replication_record"}},"created_at":"2026-05-17T23:38:14.463618+00:00","updated_at":"2026-05-17T23:38:14.463618+00:00"}