{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQZ3TJEJKEZX5SQINMPM3P3RKH","short_pith_number":"pith:RQZ3TJEJ","schema_version":"1.0","canonical_sha256":"8c33b9a48951337eca086b1ecdbf7151f4baae18b10ccd354ffd85fb159305ef","source":{"kind":"arxiv","id":"2507.00990","version":3},"attestation_state":"computed","paper":{"title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Hanlin Mai, Shivansh Patel, Shraddhaa Mohan, Svetlana Lazebnik, Unnat Jain, Yunzhu Li","submitted_at":"2025-07-01T17:39:59Z","abstract_excerpt":"This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks--such as pouring, wiping, and mixing--purely by imitating AI-generated videos, without requiring any physical demonstrations or robot-specific training. Given a language command and an initial scene image, a video diffusion model generates potential demonstration videos, and a vision-language model (VLM) automatically filters out results that do not follow the command. A 6D pose tracker then extracts object trajectories from the video, and the trajectories are ret"},"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":"2507.00990","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T17:39:59Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"b229ce2bd390c5c8e6b710e56260ed57c0d6c955742a9af418cf1325e718d8ed","abstract_canon_sha256":"918ddf54a55d597c96cce0707b64642dd8e162d273b3d6437f34914b16ae1b8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:35.255439Z","signature_b64":"TzWXVyC3bsBy38egR6uEooXLUYmERrUMt1nG5SZ+rAD3IoZM0LiDNn8oGEXBzirzbR1XXClhqdgy6YSn1Am+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c33b9a48951337eca086b1ecdbf7151f4baae18b10ccd354ffd85fb159305ef","last_reissued_at":"2026-05-18T03:09:35.254679Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:35.254679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Hanlin Mai, Shivansh Patel, Shraddhaa Mohan, Svetlana Lazebnik, Unnat Jain, Yunzhu Li","submitted_at":"2025-07-01T17:39:59Z","abstract_excerpt":"This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks--such as pouring, wiping, and mixing--purely by imitating AI-generated videos, without requiring any physical demonstrations or robot-specific training. Given a language command and an initial scene image, a video diffusion model generates potential demonstration videos, and a vision-language model (VLM) automatically filters out results that do not follow the command. A 6D pose tracker then extracts object trajectories from the video, and the trajectories are ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00990","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2507.00990","created_at":"2026-05-18T03:09:35.254786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00990v3","created_at":"2026-05-18T03:09:35.254786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00990","created_at":"2026-05-18T03:09:35.254786+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQZ3TJEJKEZX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQZ3TJEJKEZX5SQI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQZ3TJEJ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":199,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":202,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02667","citing_title":"AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH","json":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH.json","graph_json":"https://pith.science/api/pith-number/RQZ3TJEJKEZX5SQINMPM3P3RKH/graph.json","events_json":"https://pith.science/api/pith-number/RQZ3TJEJKEZX5SQINMPM3P3RKH/events.json","paper":"https://pith.science/paper/RQZ3TJEJ"},"agent_actions":{"view_html":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH","download_json":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH.json","view_paper":"https://pith.science/paper/RQZ3TJEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00990&json=true","fetch_graph":"https://pith.science/api/pith-number/RQZ3TJEJKEZX5SQINMPM3P3RKH/graph.json","fetch_events":"https://pith.science/api/pith-number/RQZ3TJEJKEZX5SQINMPM3P3RKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH/action/storage_attestation","attest_author":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH/action/author_attestation","sign_citation":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH/action/citation_signature","submit_replication":"https://pith.science/pith/RQZ3TJEJKEZX5SQINMPM3P3RKH/action/replication_record"}},"created_at":"2026-05-18T03:09:35.254786+00:00","updated_at":"2026-05-18T03:09:35.254786+00:00"}