{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FNKIZOPU3UZF53TVGZQ6C665AI","short_pith_number":"pith:FNKIZOPU","schema_version":"1.0","canonical_sha256":"2b548cb9f4dd325eee753661e17bdd023065613883b0f2003dbdcc7f62afcfb3","source":{"kind":"arxiv","id":"2310.14386","version":1},"attestation_state":"computed","paper":{"title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Peter Stone, Yifeng Zhu, Yuke Zhu, Zhenyu Jiang","submitted_at":"2023-10-22T18:51:45Z","abstract_excerpt":"We introduce GROOT, an imitation learning method for learning robust policies with object-centric and 3D priors. GROOT builds policies that generalize beyond their initial training conditions for vision-based manipulation. It constructs object-centric 3D representations that are robust toward background changes and camera views and reason over these representations using a transformer-based policy. Furthermore, we introduce a segmentation correspondence model that allows policies to generalize to new objects at test time. Through comprehensive experiments, we validate the robustness of GROOT p"},"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":"2310.14386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-22T18:51:45Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"dd2267cc2ad0ccc63d6113a40919223b0814a9ce8b8dccf9c49e891c6c3afcd1","abstract_canon_sha256":"cb7c042caa707c2cf7965542c251fbd69e72fee60bbde8a59563f677516cf3a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:43.723513Z","signature_b64":"DqlUiQo42PVjseILr/HXUsFTMf1VTJ11Ih/EkVc5BUlwZQIIc68tV50lZkshiFJkN37QmY+UJEu65vLEL+tsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b548cb9f4dd325eee753661e17bdd023065613883b0f2003dbdcc7f62afcfb3","last_reissued_at":"2026-07-05T07:03:43.723022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:43.723022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Peter Stone, Yifeng Zhu, Yuke Zhu, Zhenyu Jiang","submitted_at":"2023-10-22T18:51:45Z","abstract_excerpt":"We introduce GROOT, an imitation learning method for learning robust policies with object-centric and 3D priors. GROOT builds policies that generalize beyond their initial training conditions for vision-based manipulation. It constructs object-centric 3D representations that are robust toward background changes and camera views and reason over these representations using a transformer-based policy. Furthermore, we introduce a segmentation correspondence model that allows policies to generalize to new objects at test time. Through comprehensive experiments, we validate the robustness of GROOT p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14386","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/2310.14386/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":"2310.14386","created_at":"2026-07-05T07:03:43.723079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14386v1","created_at":"2026-07-05T07:03:43.723079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14386","created_at":"2026-07-05T07:03:43.723079+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNKIZOPU3UZF","created_at":"2026-07-05T07:03:43.723079+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNKIZOPU3UZF53TV","created_at":"2026-07-05T07:03:43.723079+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNKIZOPU","created_at":"2026-07-05T07:03:43.723079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08751","citing_title":"DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01072","citing_title":"Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26649","citing_title":"On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16043","citing_title":"Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11809","citing_title":"Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI","json":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI.json","graph_json":"https://pith.science/api/pith-number/FNKIZOPU3UZF53TVGZQ6C665AI/graph.json","events_json":"https://pith.science/api/pith-number/FNKIZOPU3UZF53TVGZQ6C665AI/events.json","paper":"https://pith.science/paper/FNKIZOPU"},"agent_actions":{"view_html":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI","download_json":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI.json","view_paper":"https://pith.science/paper/FNKIZOPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14386&json=true","fetch_graph":"https://pith.science/api/pith-number/FNKIZOPU3UZF53TVGZQ6C665AI/graph.json","fetch_events":"https://pith.science/api/pith-number/FNKIZOPU3UZF53TVGZQ6C665AI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI/action/storage_attestation","attest_author":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI/action/author_attestation","sign_citation":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI/action/citation_signature","submit_replication":"https://pith.science/pith/FNKIZOPU3UZF53TVGZQ6C665AI/action/replication_record"}},"created_at":"2026-07-05T07:03:43.723079+00:00","updated_at":"2026-07-05T07:03:43.723079+00:00"}