{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TD7AWOEBSNUIYCXB22RLQ5A24G","short_pith_number":"pith:TD7AWOEB","schema_version":"1.0","canonical_sha256":"98fe0b388193688c0ae1d6a2b8741ae1955d6f1cea33ead8a69b28f1a3761cf8","source":{"kind":"arxiv","id":"2211.13225","version":1},"attestation_state":"computed","paper":{"title":"Learning to Imitate Object Interactions from Internet Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew Wang, Austin Patel, Ilija Radosavovic, Jitendra Malik","submitted_at":"2022-11-23T18:59:07Z","abstract_excerpt":"We study the problem of imitating object interactions from Internet videos. This requires understanding the hand-object interactions in 4D, spatially in 3D and over time, which is challenging due to mutual hand-object occlusions. In this paper we make two main contributions: (1) a novel reconstruction technique RHOV (Reconstructing Hands and Objects from Videos), which reconstructs 4D trajectories of both the hand and the object using 2D image cues and temporal smoothness constraints; (2) a system for imitating object interactions in a physics simulator with reinforcement learning. We apply ou"},"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":"2211.13225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T18:59:07Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"dafb2a8ac5ce9155716eabb181d4caf94061c127981159c8c4e94e1ed2922e32","abstract_canon_sha256":"b09c6c493ebde9e4f594483a00c9babac74feb13bc429480244de0f25e811a3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:59.540681Z","signature_b64":"FKlIstRyf5gE5gPhuMHo6xePGZ/XA2Y0/xggpoX1dVx9qaL5lH4KMLn0NJ4kcdUK7kJr38KJJn/cd6ZB8rCeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98fe0b388193688c0ae1d6a2b8741ae1955d6f1cea33ead8a69b28f1a3761cf8","last_reissued_at":"2026-07-05T05:18:59.540181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:59.540181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Imitate Object Interactions from Internet Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew Wang, Austin Patel, Ilija Radosavovic, Jitendra Malik","submitted_at":"2022-11-23T18:59:07Z","abstract_excerpt":"We study the problem of imitating object interactions from Internet videos. This requires understanding the hand-object interactions in 4D, spatially in 3D and over time, which is challenging due to mutual hand-object occlusions. In this paper we make two main contributions: (1) a novel reconstruction technique RHOV (Reconstructing Hands and Objects from Videos), which reconstructs 4D trajectories of both the hand and the object using 2D image cues and temporal smoothness constraints; (2) a system for imitating object interactions in a physics simulator with reinforcement learning. We apply ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13225","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/2211.13225/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":"2211.13225","created_at":"2026-07-05T05:18:59.540241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13225v1","created_at":"2026-07-05T05:18:59.540241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13225","created_at":"2026-07-05T05:18:59.540241+00:00"},{"alias_kind":"pith_short_12","alias_value":"TD7AWOEBSNUI","created_at":"2026-07-05T05:18:59.540241+00:00"},{"alias_kind":"pith_short_16","alias_value":"TD7AWOEBSNUIYCXB","created_at":"2026-07-05T05:18:59.540241+00:00"},{"alias_kind":"pith_short_8","alias_value":"TD7AWOEB","created_at":"2026-07-05T05:18:59.540241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10743","citing_title":"Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30598","citing_title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G","json":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G.json","graph_json":"https://pith.science/api/pith-number/TD7AWOEBSNUIYCXB22RLQ5A24G/graph.json","events_json":"https://pith.science/api/pith-number/TD7AWOEBSNUIYCXB22RLQ5A24G/events.json","paper":"https://pith.science/paper/TD7AWOEB"},"agent_actions":{"view_html":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G","download_json":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G.json","view_paper":"https://pith.science/paper/TD7AWOEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13225&json=true","fetch_graph":"https://pith.science/api/pith-number/TD7AWOEBSNUIYCXB22RLQ5A24G/graph.json","fetch_events":"https://pith.science/api/pith-number/TD7AWOEBSNUIYCXB22RLQ5A24G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G/action/storage_attestation","attest_author":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G/action/author_attestation","sign_citation":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G/action/citation_signature","submit_replication":"https://pith.science/pith/TD7AWOEBSNUIYCXB22RLQ5A24G/action/replication_record"}},"created_at":"2026-07-05T05:18:59.540241+00:00","updated_at":"2026-07-05T05:18:59.540241+00:00"}