{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V2IKBPV477V7CQFDJZPC34OSJK","short_pith_number":"pith:V2IKBPV4","schema_version":"1.0","canonical_sha256":"ae90a0bebcffebf140a34e5e2df1d24ab699a767b87c1b29a518e24915fd0933","source":{"kind":"arxiv","id":"2302.12422","version":2},"attestation_state":"computed","paper":{"title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Anima Anandkumar, Chen Wang, Danfei Xu, Jiankai Sun, Li Fei-Fei, Linxi Fan, Ruohan Zhang, Yuke Zhu","submitted_at":"2023-02-24T02:54:15Z","abstract_excerpt":"Imitation learning from human demonstrations is a promising paradigm for teaching robots manipulation skills in the real world. However, learning complex long-horizon tasks often requires an unattainable amount of demonstrations. To reduce the high data requirement, we resort to human play data - video sequences of people freely interacting with the environment using their hands. Even with different morphologies, we hypothesize that human play data contain rich and salient information about physical interactions that can readily facilitate robot policy learning. Motivated by this, we introduce"},"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":"2302.12422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-24T02:54:15Z","cross_cats_sorted":[],"title_canon_sha256":"d58f456fe6620a45efd57f000a2282594e6f4ae27918dfa40abc2a401f7cf833","abstract_canon_sha256":"ce5cfd5dc9c22c8f5ae095c70fe4df5aac94b939a8c815956778e8b22c93e95c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:21.425976Z","signature_b64":"xrogosLixzstLD6BWMK9XXF9DZR7KOMuQ0lQ7bOs+NXwg6I610GRKbFsgmUm5Ee85sp71L7dN38jGmgB0ZUyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae90a0bebcffebf140a34e5e2df1d24ab699a767b87c1b29a518e24915fd0933","last_reissued_at":"2026-07-05T07:00:21.425509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:21.425509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Anima Anandkumar, Chen Wang, Danfei Xu, Jiankai Sun, Li Fei-Fei, Linxi Fan, Ruohan Zhang, Yuke Zhu","submitted_at":"2023-02-24T02:54:15Z","abstract_excerpt":"Imitation learning from human demonstrations is a promising paradigm for teaching robots manipulation skills in the real world. However, learning complex long-horizon tasks often requires an unattainable amount of demonstrations. To reduce the high data requirement, we resort to human play data - video sequences of people freely interacting with the environment using their hands. Even with different morphologies, we hypothesize that human play data contain rich and salient information about physical interactions that can readily facilitate robot policy learning. Motivated by this, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12422","kind":"arxiv","version":2},"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/2302.12422/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":"2302.12422","created_at":"2026-07-05T07:00:21.425566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12422v2","created_at":"2026-07-05T07:00:21.425566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12422","created_at":"2026-07-05T07:00:21.425566+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2IKBPV477V7","created_at":"2026-07-05T07:00:21.425566+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2IKBPV477V7CQFD","created_at":"2026-07-05T07:00:21.425566+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2IKBPV4","created_at":"2026-07-05T07:00:21.425566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06988","citing_title":"WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26428","citing_title":"Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23685","citing_title":"LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17055","citing_title":"T-Rex: Tactile-Reactive Dexterous Manipulation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17054","citing_title":"Human Universal Grasping","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12109","citing_title":"Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10025","citing_title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08548","citing_title":"OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01851","citing_title":"PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28133","citing_title":"Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28813","citing_title":"Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29298","citing_title":"MonoDuo: Using One Robot Arm to Learn Bimanual Policies","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17001","citing_title":"Unify Robot Actions in Camera Frame","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15659","citing_title":"FLARE: Robot Learning with Implicit World Modeling","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":43,"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":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02792","citing_title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK","json":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK.json","graph_json":"https://pith.science/api/pith-number/V2IKBPV477V7CQFDJZPC34OSJK/graph.json","events_json":"https://pith.science/api/pith-number/V2IKBPV477V7CQFDJZPC34OSJK/events.json","paper":"https://pith.science/paper/V2IKBPV4"},"agent_actions":{"view_html":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK","download_json":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK.json","view_paper":"https://pith.science/paper/V2IKBPV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12422&json=true","fetch_graph":"https://pith.science/api/pith-number/V2IKBPV477V7CQFDJZPC34OSJK/graph.json","fetch_events":"https://pith.science/api/pith-number/V2IKBPV477V7CQFDJZPC34OSJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK/action/storage_attestation","attest_author":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK/action/author_attestation","sign_citation":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK/action/citation_signature","submit_replication":"https://pith.science/pith/V2IKBPV477V7CQFDJZPC34OSJK/action/replication_record"}},"created_at":"2026-07-05T07:00:21.425566+00:00","updated_at":"2026-07-05T07:00:21.425566+00:00"}