{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2KEIHSYFJRLGH37ODFKJ7Q6QV5","short_pith_number":"pith:2KEIHSYF","schema_version":"1.0","canonical_sha256":"d28883cb054c5663efee19549fc3d0af7a119a7c99f19fe63f41e5fa5e0d7ece","source":{"kind":"arxiv","id":"2509.00361","version":1},"attestation_state":"computed","paper":{"title":"Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-Top Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuye Zhang, Linfang Zheng, Wei Pan, Wei Zhang, Xiaoxiong Zhang","submitted_at":"2025-08-30T04:53:32Z","abstract_excerpt":"Robotic manipulation in unstructured environments requires systems that can generalize across diverse tasks while maintaining robust and reliable performance. We introduce {GVF-TAPE}, a closed-loop framework that combines generative visual foresight with task-agnostic pose estimation to enable scalable robotic manipulation. GVF-TAPE employs a generative video model to predict future RGB-D frames from a single side-view RGB image and a task description, offering visual plans that guide robot actions. A decoupled pose estimation model then extracts end-effector poses from the predicted frames, t"},"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":"2509.00361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-30T04:53:32Z","cross_cats_sorted":[],"title_canon_sha256":"e23a35daa4cb97edae24d6356e00af3602a1f7bee6b7a422b6337897052a74e4","abstract_canon_sha256":"f69564c41f7cf8a1740cd526bb3921c464123512e64839b1e9294cc7cc6a0d7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:14.640445Z","signature_b64":"bCeJ/jwiW04a5lPDzdajzKBBeEYmt8RvxcZ3efuSyCvUyCDC1gSwsy6xf7Ysw3k8GVaUiDsmqrjkJi36mrJLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d28883cb054c5663efee19549fc3d0af7a119a7c99f19fe63f41e5fa5e0d7ece","last_reissued_at":"2026-07-05T12:02:14.639957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:14.639957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-Top Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuye Zhang, Linfang Zheng, Wei Pan, Wei Zhang, Xiaoxiong Zhang","submitted_at":"2025-08-30T04:53:32Z","abstract_excerpt":"Robotic manipulation in unstructured environments requires systems that can generalize across diverse tasks while maintaining robust and reliable performance. We introduce {GVF-TAPE}, a closed-loop framework that combines generative visual foresight with task-agnostic pose estimation to enable scalable robotic manipulation. GVF-TAPE employs a generative video model to predict future RGB-D frames from a single side-view RGB image and a task description, offering visual plans that guide robot actions. A decoupled pose estimation model then extracts end-effector poses from the predicted frames, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00361","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/2509.00361/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":"2509.00361","created_at":"2026-07-05T12:02:14.640011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00361v1","created_at":"2026-07-05T12:02:14.640011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00361","created_at":"2026-07-05T12:02:14.640011+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KEIHSYFJRLG","created_at":"2026-07-05T12:02:14.640011+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KEIHSYFJRLGH37O","created_at":"2026-07-05T12:02:14.640011+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KEIHSYF","created_at":"2026-07-05T12:02:14.640011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":28,"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":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5","json":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5.json","graph_json":"https://pith.science/api/pith-number/2KEIHSYFJRLGH37ODFKJ7Q6QV5/graph.json","events_json":"https://pith.science/api/pith-number/2KEIHSYFJRLGH37ODFKJ7Q6QV5/events.json","paper":"https://pith.science/paper/2KEIHSYF"},"agent_actions":{"view_html":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5","download_json":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5.json","view_paper":"https://pith.science/paper/2KEIHSYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00361&json=true","fetch_graph":"https://pith.science/api/pith-number/2KEIHSYFJRLGH37ODFKJ7Q6QV5/graph.json","fetch_events":"https://pith.science/api/pith-number/2KEIHSYFJRLGH37ODFKJ7Q6QV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5/action/storage_attestation","attest_author":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5/action/author_attestation","sign_citation":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5/action/citation_signature","submit_replication":"https://pith.science/pith/2KEIHSYFJRLGH37ODFKJ7Q6QV5/action/replication_record"}},"created_at":"2026-07-05T12:02:14.640011+00:00","updated_at":"2026-07-05T12:02:14.640011+00:00"}