{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4LHBRPBSF7SX2LCESDXMZMGAOT","short_pith_number":"pith:4LHBRPBS","schema_version":"1.0","canonical_sha256":"e2ce18bc322fe57d2c4490eeccb0c074e7d56a58c66ff6bae5d4273ae133d631","source":{"kind":"arxiv","id":"2302.12766","version":1},"attestation_state":"computed","paper":{"title":"Language-Driven Representation Learning for Robotics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Annie S. Chen, Chelsea Finn, Dorsa Sadigh, Percy Liang, Siddharth Karamcheti, Suraj Nair, Thomas Kollar","submitted_at":"2023-02-24T17:29:31Z","abstract_excerpt":"Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these representations exhibit strong transfer to policy learning for visuomotor control. But, robot learning encompasses a diverse set of problems beyond control including grasp affordance prediction, language-conditioned imitation learning, and intent scoring for human-robot collaboration, amongst others. First, we demonstrate that existing representations yield "},"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":"2302.12766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-02-24T17:29:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"e402af7878d633f4c573cfe7bcbe981ddee740454318bbbf99b0750bf08a7474","abstract_canon_sha256":"d823dc710863747c728cf3a1202bb4fbe178faa6d30adeaa27d32a49af809a27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:21.042505Z","signature_b64":"Hd/iGG7govgoSJrDWu8Ov01VE69V3GB3cZSGl4dD7YmKdEfzGqVS1ck1f2ap5EjRRZxB2pcodHe2jyDCY6TRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2ce18bc322fe57d2c4490eeccb0c074e7d56a58c66ff6bae5d4273ae133d631","last_reissued_at":"2026-07-05T05:45:21.042113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:21.042113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Driven Representation Learning for Robotics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Annie S. Chen, Chelsea Finn, Dorsa Sadigh, Percy Liang, Siddharth Karamcheti, Suraj Nair, Thomas Kollar","submitted_at":"2023-02-24T17:29:31Z","abstract_excerpt":"Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these representations exhibit strong transfer to policy learning for visuomotor control. But, robot learning encompasses a diverse set of problems beyond control including grasp affordance prediction, language-conditioned imitation learning, and intent scoring for human-robot collaboration, amongst others. First, we demonstrate that existing representations yield "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12766","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/2302.12766/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":"2302.12766","created_at":"2026-07-05T05:45:21.042169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12766v1","created_at":"2026-07-05T05:45:21.042169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12766","created_at":"2026-07-05T05:45:21.042169+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LHBRPBSF7SX","created_at":"2026-07-05T05:45:21.042169+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LHBRPBSF7SX2LCE","created_at":"2026-07-05T05:45:21.042169+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LHBRPBS","created_at":"2026-07-05T05:45:21.042169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06564","citing_title":"Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24448","citing_title":"Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17200","citing_title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00784","citing_title":"LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04046","citing_title":"Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16241","citing_title":"Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17077","citing_title":"How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2311.01378","citing_title":"Vision-Language Foundation Models as Effective Robot Imitators","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":35,"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":80,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14803","citing_title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06158","citing_title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14734","citing_title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09246","citing_title":"OpenVLA: An Open-Source Vision-Language-Action Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT","json":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT.json","graph_json":"https://pith.science/api/pith-number/4LHBRPBSF7SX2LCESDXMZMGAOT/graph.json","events_json":"https://pith.science/api/pith-number/4LHBRPBSF7SX2LCESDXMZMGAOT/events.json","paper":"https://pith.science/paper/4LHBRPBS"},"agent_actions":{"view_html":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT","download_json":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT.json","view_paper":"https://pith.science/paper/4LHBRPBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12766&json=true","fetch_graph":"https://pith.science/api/pith-number/4LHBRPBSF7SX2LCESDXMZMGAOT/graph.json","fetch_events":"https://pith.science/api/pith-number/4LHBRPBSF7SX2LCESDXMZMGAOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT/action/storage_attestation","attest_author":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT/action/author_attestation","sign_citation":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT/action/citation_signature","submit_replication":"https://pith.science/pith/4LHBRPBSF7SX2LCESDXMZMGAOT/action/replication_record"}},"created_at":"2026-07-05T05:45:21.042169+00:00","updated_at":"2026-07-05T05:45:21.042169+00:00"}