{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CP34PCEBDRRG6E4VKUVAZGSROI","short_pith_number":"pith:CP34PCEB","schema_version":"1.0","canonical_sha256":"13f7c788811c626f1395552a0c9a517235c08e1ef3e285552c4630286173ffe6","source":{"kind":"arxiv","id":"2505.03729","version":5},"attestation_state":"computed","paper":{"title":"Visual Imitation Enables Contextual Humanoid Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Angjoo Kanazawa, Anthony Zhang, Arthur Allshire, Chung Min Kim, David McAllister, Hongsuk Choi, Jitendra Malik, Junyi Zhang, Pieter Abbeel, Trevor Darrell","submitted_at":"2025-05-06T17:57:12Z","abstract_excerpt":"How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce VIDEOMIMIC, a real-to-sim-to-real pipeline that mines everyday videos, jointly reconstructs the humans and the environment, and produces whole-body control policies for humanoid robots that perform the corresponding skills. We demonstrate the results of our pipeline on real humanoid robots, showing robust, repeatable contextual control such as staircase ascents and"},"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":"2505.03729","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-06T17:57:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3867151caa79b27927882207f385fa80ca8521295ea82d92c9e5b065ddd32ad5","abstract_canon_sha256":"9175104cecbfe3d24a90fe7d1bf84350a8b68cf48dc42307ee7eb740a71bbbb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:22.580502Z","signature_b64":"qFpxopTNnxg317hC3pLrMSuStV1qVuTIOYyjIXHpcVOZjlP0+IfHiX76A3mnGgEiiwkaGmQBF6bTF/rhekzEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f7c788811c626f1395552a0c9a517235c08e1ef3e285552c4630286173ffe6","last_reissued_at":"2026-07-05T12:01:22.579990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:22.579990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Imitation Enables Contextual Humanoid Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Angjoo Kanazawa, Anthony Zhang, Arthur Allshire, Chung Min Kim, David McAllister, Hongsuk Choi, Jitendra Malik, Junyi Zhang, Pieter Abbeel, Trevor Darrell","submitted_at":"2025-05-06T17:57:12Z","abstract_excerpt":"How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce VIDEOMIMIC, a real-to-sim-to-real pipeline that mines everyday videos, jointly reconstructs the humans and the environment, and produces whole-body control policies for humanoid robots that perform the corresponding skills. We demonstrate the results of our pipeline on real humanoid robots, showing robust, repeatable contextual control such as staircase ascents and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03729","kind":"arxiv","version":5},"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/2505.03729/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":"2505.03729","created_at":"2026-07-05T12:01:22.580047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03729v5","created_at":"2026-07-05T12:01:22.580047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03729","created_at":"2026-07-05T12:01:22.580047+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP34PCEBDRRG","created_at":"2026-07-05T12:01:22.580047+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP34PCEBDRRG6E4V","created_at":"2026-07-05T12:01:22.580047+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP34PCEB","created_at":"2026-07-05T12:01:22.580047+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.07370","citing_title":"Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08742","citing_title":"ContactMimic: Humanoid Object Interaction via Contact Control","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07370","citing_title":"Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24448","citing_title":"Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26215","citing_title":"TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05160","citing_title":"GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00252","citing_title":"HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03205","citing_title":"HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15517","citing_title":"Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27711","citing_title":"ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI","json":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI.json","graph_json":"https://pith.science/api/pith-number/CP34PCEBDRRG6E4VKUVAZGSROI/graph.json","events_json":"https://pith.science/api/pith-number/CP34PCEBDRRG6E4VKUVAZGSROI/events.json","paper":"https://pith.science/paper/CP34PCEB"},"agent_actions":{"view_html":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI","download_json":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI.json","view_paper":"https://pith.science/paper/CP34PCEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03729&json=true","fetch_graph":"https://pith.science/api/pith-number/CP34PCEBDRRG6E4VKUVAZGSROI/graph.json","fetch_events":"https://pith.science/api/pith-number/CP34PCEBDRRG6E4VKUVAZGSROI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI/action/storage_attestation","attest_author":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI/action/author_attestation","sign_citation":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI/action/citation_signature","submit_replication":"https://pith.science/pith/CP34PCEBDRRG6E4VKUVAZGSROI/action/replication_record"}},"created_at":"2026-07-05T12:01:22.580047+00:00","updated_at":"2026-07-05T12:01:22.580047+00:00"}