{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3BG7HOLAXKXHGSBZ6X2SES56VR","short_pith_number":"pith:3BG7HOLA","schema_version":"1.0","canonical_sha256":"d84df3b960baae734839f5f5224bbeac66b02f502038d00d3a26811dbca2e490","source":{"kind":"arxiv","id":"2303.00905","version":2},"attestation_state":"computed","paper":{"title":"Open-World Object Manipulation using Pre-trained Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Austin Stone, Brianna Zitkovich, Chelsea Finn, Fei Xia, Karol Hausman, Keerthana Gopalakrishnan, Kuang-Huei Lee, Paul Wohlhart, Quan Vuong, Sean Kirmani, Ted Xiao, Yao Lu","submitted_at":"2023-03-02T01:55:10Z","abstract_excerpt":"For robots to follow instructions from people, they must be able to connect the rich semantic information in human vocabulary, e.g. \"can you get me the pink stuffed whale?\" to their sensory observations and actions. This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information. We would like a robot's policy to be able to perceive and pick up the pink stuffed whale, even if it has never seen "},"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":"2303.00905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T01:55:10Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a297365138be677953db3a6b490d8875484e4743c7d71156666cb1a16b8970f2","abstract_canon_sha256":"8dc248e53673db7b6e7380c57baa0e1165deedb9dfb45ac6b9ea256deb3f76e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:06.724766Z","signature_b64":"Q3mrUDb4fbPC2crDW4Rxdp4nvaidtPwEQWCEScRsD5glEE013BVFHDdHj4kNlCudr/bjV2w2sksyOgm0ikxbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d84df3b960baae734839f5f5224bbeac66b02f502038d00d3a26811dbca2e490","last_reissued_at":"2026-07-05T07:05:06.724224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:06.724224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-World Object Manipulation using Pre-trained Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Austin Stone, Brianna Zitkovich, Chelsea Finn, Fei Xia, Karol Hausman, Keerthana Gopalakrishnan, Kuang-Huei Lee, Paul Wohlhart, Quan Vuong, Sean Kirmani, Ted Xiao, Yao Lu","submitted_at":"2023-03-02T01:55:10Z","abstract_excerpt":"For robots to follow instructions from people, they must be able to connect the rich semantic information in human vocabulary, e.g. \"can you get me the pink stuffed whale?\" to their sensory observations and actions. This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information. We would like a robot's policy to be able to perceive and pick up the pink stuffed whale, even if it has never seen "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00905","kind":"arxiv","version":2},"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/2303.00905/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":"2303.00905","created_at":"2026-07-05T07:05:06.724281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00905v2","created_at":"2026-07-05T07:05:06.724281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00905","created_at":"2026-07-05T07:05:06.724281+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BG7HOLAXKXH","created_at":"2026-07-05T07:05:06.724281+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BG7HOLAXKXHGSBZ","created_at":"2026-07-05T07:05:06.724281+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BG7HOLA","created_at":"2026-07-05T07:05:06.724281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25585","citing_title":"FeVOS: Foresight Expression Video Object Segmentation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26588","citing_title":"Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12910","citing_title":"Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16054","citing_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15279","citing_title":"Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03233","citing_title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19417","citing_title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11114","citing_title":"SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2310.08864","citing_title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00438","citing_title":"Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09246","citing_title":"OpenVLA: An Open-Source Vision-Language-Action Model","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15483","citing_title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR","json":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR.json","graph_json":"https://pith.science/api/pith-number/3BG7HOLAXKXHGSBZ6X2SES56VR/graph.json","events_json":"https://pith.science/api/pith-number/3BG7HOLAXKXHGSBZ6X2SES56VR/events.json","paper":"https://pith.science/paper/3BG7HOLA"},"agent_actions":{"view_html":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR","download_json":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR.json","view_paper":"https://pith.science/paper/3BG7HOLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00905&json=true","fetch_graph":"https://pith.science/api/pith-number/3BG7HOLAXKXHGSBZ6X2SES56VR/graph.json","fetch_events":"https://pith.science/api/pith-number/3BG7HOLAXKXHGSBZ6X2SES56VR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR/action/storage_attestation","attest_author":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR/action/author_attestation","sign_citation":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR/action/citation_signature","submit_replication":"https://pith.science/pith/3BG7HOLAXKXHGSBZ6X2SES56VR/action/replication_record"}},"created_at":"2026-07-05T07:05:06.724281+00:00","updated_at":"2026-07-05T07:05:06.724281+00:00"}