{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q5OCAJ6TMQHF7ITUPETUA2AY3I","short_pith_number":"pith:Q5OCAJ6T","schema_version":"1.0","canonical_sha256":"875c2027d3640e5fa2747927406818da0d1129b832ce163012d4f8d1c451f610","source":{"kind":"arxiv","id":"2406.18915","version":3},"attestation_state":"computed","paper":{"title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Dieter Fox, Jiafei Duan, Kiana Ehsani, Ranjay Krishna, Wentao Yuan, Wilbert Pumacay, Yi Ru Wang","submitted_at":"2024-06-27T06:12:01Z","abstract_excerpt":"Large-scale endeavors like and widespread community efforts such as Open-X-Embodiment have contributed to growing the scale of robot demonstration data. However, there is still an opportunity to improve the quality, quantity, and diversity of robot demonstration data. Although vision-language models have been shown to automatically generate demonstration data, their utility has been limited to environments with privileged state information, they require hand-designed skills, and are limited to interactions with few object instances. We propose Manipulate-Anything, a scalable automated generati"},"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":"2406.18915","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-27T06:12:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ae7add4638b8de690a6b2da102335a4d48bbd4f7f41a7203fe17cf107a21a882","abstract_canon_sha256":"cae5dc4410d00af269b259f9f1a07436546361941fd44d4e88d209e536f24247"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:37.899889Z","signature_b64":"ud3QGmnGq3VzxzdYMhEy9jCipZCGEWbsodzno3bc0RJd7BaDHhxlIzRIa+Yxy1zNEFN5RG1FjlVku0INBLU/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"875c2027d3640e5fa2747927406818da0d1129b832ce163012d4f8d1c451f610","last_reissued_at":"2026-07-05T09:00:37.899423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:37.899423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Dieter Fox, Jiafei Duan, Kiana Ehsani, Ranjay Krishna, Wentao Yuan, Wilbert Pumacay, Yi Ru Wang","submitted_at":"2024-06-27T06:12:01Z","abstract_excerpt":"Large-scale endeavors like and widespread community efforts such as Open-X-Embodiment have contributed to growing the scale of robot demonstration data. However, there is still an opportunity to improve the quality, quantity, and diversity of robot demonstration data. Although vision-language models have been shown to automatically generate demonstration data, their utility has been limited to environments with privileged state information, they require hand-designed skills, and are limited to interactions with few object instances. We propose Manipulate-Anything, a scalable automated generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18915","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.18915/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":"2406.18915","created_at":"2026-07-05T09:00:37.899480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18915v3","created_at":"2026-07-05T09:00:37.899480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18915","created_at":"2026-07-05T09:00:37.899480+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5OCAJ6TMQHF","created_at":"2026-07-05T09:00:37.899480+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5OCAJ6TMQHF7ITU","created_at":"2026-07-05T09:00:37.899480+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5OCAJ6T","created_at":"2026-07-05T09:00:37.899480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24884","citing_title":"InSight: Self-Guided Skill Acquisition via Steerable VLAs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26423","citing_title":"CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26423","citing_title":"CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation","ref_index":22,"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":24,"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":51,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11951","citing_title":"From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I","json":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I.json","graph_json":"https://pith.science/api/pith-number/Q5OCAJ6TMQHF7ITUPETUA2AY3I/graph.json","events_json":"https://pith.science/api/pith-number/Q5OCAJ6TMQHF7ITUPETUA2AY3I/events.json","paper":"https://pith.science/paper/Q5OCAJ6T"},"agent_actions":{"view_html":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I","download_json":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I.json","view_paper":"https://pith.science/paper/Q5OCAJ6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18915&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5OCAJ6TMQHF7ITUPETUA2AY3I/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5OCAJ6TMQHF7ITUPETUA2AY3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I/action/storage_attestation","attest_author":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I/action/author_attestation","sign_citation":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I/action/citation_signature","submit_replication":"https://pith.science/pith/Q5OCAJ6TMQHF7ITUPETUA2AY3I/action/replication_record"}},"created_at":"2026-07-05T09:00:37.899480+00:00","updated_at":"2026-07-05T09:00:37.899480+00:00"}