{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7UHR7KAH3DS45OZPTPOCVOI7JD","short_pith_number":"pith:7UHR7KAH","schema_version":"1.0","canonical_sha256":"fd0f1fa807d8e5cebb2f9bdc2ab91f48d843246ed96027602c09eac175a17135","source":{"kind":"arxiv","id":"2302.06671","version":2},"attestation_state":"computed","paper":{"title":"GenAug: Retargeting behaviors to unseen situations via Generative Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Sho Kiami, Vikash Kumar, Zoey Chen","submitted_at":"2023-02-13T20:18:25Z","abstract_excerpt":"Robot learning methods have the potential for widespread generalization across tasks, environments, and objects. However, these methods require large diverse datasets that are expensive to collect in real-world robotics settings. For robot learning to generalize, we must be able to leverage sources of data or priors beyond the robot's own experience. In this work, we posit that image-text generative models, which are pre-trained on large corpora of web-scraped data, can serve as such a data source. We show that despite these generative models being trained on largely non-robotics data, they ca"},"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":"2302.06671","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-02-13T20:18:25Z","cross_cats_sorted":[],"title_canon_sha256":"12e8ab6654cbc5888764594a4a85532846f5cf8ebb6009a97e35626cd7e24b9b","abstract_canon_sha256":"eb9dc943173bfeacb27709fc3b418f102132c7fb60eefe003912a1a14ffc64ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:52.736741Z","signature_b64":"IXuwI3YIpp0V3X0PYB7hVlD6z6zAIoeq8I+MZDm2QmvkZOb2hdGq2/oIWqtMW0MFWMA/xFB98cHbeGqZFY0aAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd0f1fa807d8e5cebb2f9bdc2ab91f48d843246ed96027602c09eac175a17135","last_reissued_at":"2026-07-05T05:44:52.736260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:52.736260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenAug: Retargeting behaviors to unseen situations via Generative Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Sho Kiami, Vikash Kumar, Zoey Chen","submitted_at":"2023-02-13T20:18:25Z","abstract_excerpt":"Robot learning methods have the potential for widespread generalization across tasks, environments, and objects. However, these methods require large diverse datasets that are expensive to collect in real-world robotics settings. For robot learning to generalize, we must be able to leverage sources of data or priors beyond the robot's own experience. In this work, we posit that image-text generative models, which are pre-trained on large corpora of web-scraped data, can serve as such a data source. We show that despite these generative models being trained on largely non-robotics data, they ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06671","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/2302.06671/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":"2302.06671","created_at":"2026-07-05T05:44:52.736324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06671v2","created_at":"2026-07-05T05:44:52.736324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06671","created_at":"2026-07-05T05:44:52.736324+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UHR7KAH3DS4","created_at":"2026-07-05T05:44:52.736324+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UHR7KAH3DS45OZP","created_at":"2026-07-05T05:44:52.736324+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UHR7KAH","created_at":"2026-07-05T05:44:52.736324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20118","citing_title":"Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07306","citing_title":"BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00664","citing_title":"SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19289","citing_title":"What Makes Synthetic Data Effective in Image Segmentation","ref_index":5,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2302.11550","citing_title":"Scaling Robot Learning with Semantically Imagined Experience","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":194,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":194,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00244","citing_title":"Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07306","citing_title":"BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":193,"is_internal_anchor":false},{"citing_arxiv_id":"2405.12213","citing_title":"Octo: An Open-Source Generalist Robot Policy","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14734","citing_title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","ref_index":20,"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":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15023","citing_title":"DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD","json":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD.json","graph_json":"https://pith.science/api/pith-number/7UHR7KAH3DS45OZPTPOCVOI7JD/graph.json","events_json":"https://pith.science/api/pith-number/7UHR7KAH3DS45OZPTPOCVOI7JD/events.json","paper":"https://pith.science/paper/7UHR7KAH"},"agent_actions":{"view_html":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD","download_json":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD.json","view_paper":"https://pith.science/paper/7UHR7KAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06671&json=true","fetch_graph":"https://pith.science/api/pith-number/7UHR7KAH3DS45OZPTPOCVOI7JD/graph.json","fetch_events":"https://pith.science/api/pith-number/7UHR7KAH3DS45OZPTPOCVOI7JD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD/action/storage_attestation","attest_author":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD/action/author_attestation","sign_citation":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD/action/citation_signature","submit_replication":"https://pith.science/pith/7UHR7KAH3DS45OZPTPOCVOI7JD/action/replication_record"}},"created_at":"2026-07-05T05:44:52.736324+00:00","updated_at":"2026-07-05T05:44:52.736324+00:00"}