{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S5XLA6MA4PZ5OMSHW4DSAYYF2B","short_pith_number":"pith:S5XLA6MA","schema_version":"1.0","canonical_sha256":"976eb07980e3f3d73247b707206305d04c55402f17552e6febe8cd52e9d12c77","source":{"kind":"arxiv","id":"2409.18121","version":1},"attestation_state":"computed","paper":{"title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Angjoo Kanazawa, Brent Yi, Chung Min Kim, Justin Kerr, Ken Goldberg, Mingxuan Wu, Qianqian Wang","submitted_at":"2024-09-26T17:57:16Z","abstract_excerpt":"Humans can learn to manipulate new objects by simply watching others; providing robots with the ability to learn from such demonstrations would enable a natural interface specifying new behaviors. This work develops Robot See Robot Do (RSRD), a method for imitating articulated object manipulation from a single monocular RGB human demonstration given a single static multi-view object scan. We first propose 4D Differentiable Part Models (4D-DPM), a method for recovering 3D part motion from a monocular video with differentiable rendering. This analysis-by-synthesis approach uses part-centric feat"},"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":"2409.18121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T17:57:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c37793cfcf31dade9119df3eb8376f8212f92eef605fa0d740f3e3705f559b80","abstract_canon_sha256":"a3f083030f1e6b15c7799aefb21c07b390a04fe9a319f17e6de591980641e9ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:21.013940Z","signature_b64":"oPYOxoD9ZimO2vcOelyOZpYEZB8B5uf4QjWKwbBUulstZ/gqGQhTR1z0ypZpbvb9MSpDgSba74PE8XPENuvRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"976eb07980e3f3d73247b707206305d04c55402f17552e6febe8cd52e9d12c77","last_reissued_at":"2026-07-05T09:12:21.013485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:21.013485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Angjoo Kanazawa, Brent Yi, Chung Min Kim, Justin Kerr, Ken Goldberg, Mingxuan Wu, Qianqian Wang","submitted_at":"2024-09-26T17:57:16Z","abstract_excerpt":"Humans can learn to manipulate new objects by simply watching others; providing robots with the ability to learn from such demonstrations would enable a natural interface specifying new behaviors. This work develops Robot See Robot Do (RSRD), a method for imitating articulated object manipulation from a single monocular RGB human demonstration given a single static multi-view object scan. We first propose 4D Differentiable Part Models (4D-DPM), a method for recovering 3D part motion from a monocular video with differentiable rendering. This analysis-by-synthesis approach uses part-centric feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18121","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/2409.18121/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":"2409.18121","created_at":"2026-07-05T09:12:21.013537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18121v1","created_at":"2026-07-05T09:12:21.013537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18121","created_at":"2026-07-05T09:12:21.013537+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5XLA6MA4PZ5","created_at":"2026-07-05T09:12:21.013537+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5XLA6MA4PZ5OMSH","created_at":"2026-07-05T09:12:21.013537+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5XLA6MA","created_at":"2026-07-05T09:12:21.013537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08103","citing_title":"Revisiting Articulated Parts Perception in Robot Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24403","citing_title":"Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30347","citing_title":"NeuROK: Generative 4D Neural Object Kinematics","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08547","citing_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","ref_index":14,"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":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B","json":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B.json","graph_json":"https://pith.science/api/pith-number/S5XLA6MA4PZ5OMSHW4DSAYYF2B/graph.json","events_json":"https://pith.science/api/pith-number/S5XLA6MA4PZ5OMSHW4DSAYYF2B/events.json","paper":"https://pith.science/paper/S5XLA6MA"},"agent_actions":{"view_html":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B","download_json":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B.json","view_paper":"https://pith.science/paper/S5XLA6MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18121&json=true","fetch_graph":"https://pith.science/api/pith-number/S5XLA6MA4PZ5OMSHW4DSAYYF2B/graph.json","fetch_events":"https://pith.science/api/pith-number/S5XLA6MA4PZ5OMSHW4DSAYYF2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B/action/storage_attestation","attest_author":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B/action/author_attestation","sign_citation":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B/action/citation_signature","submit_replication":"https://pith.science/pith/S5XLA6MA4PZ5OMSHW4DSAYYF2B/action/replication_record"}},"created_at":"2026-07-05T09:12:21.013537+00:00","updated_at":"2026-07-05T09:12:21.013537+00:00"}