{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ELOZOK6EURDU6LP4NN4O26FZ4N","short_pith_number":"pith:ELOZOK6E","schema_version":"1.0","canonical_sha256":"22dd972bc4a4474f2dfc6b78ed78b9e3464f4fa3a31b122fad0f0c745f7f1a10","source":{"kind":"arxiv","id":"2403.12910","version":1},"attestation_state":"computed","paper":{"title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Archit Sharma, Chelsea Finn, Jianlan Luo, Karl Pertsch, Lucy Xiaoyang Shi, Sergey Levine, Tony Z. Zhao, Zheyuan Hu","submitted_at":"2024-03-19T17:08:24Z","abstract_excerpt":"Hierarchical policies that combine language and low-level control have been shown to perform impressively long-horizon robotic tasks, by leveraging either zero-shot high-level planners like pretrained language and vision-language models (LLMs/VLMs) or models trained on annotated robotic demonstrations. However, for complex and dexterous skills, attaining high success rates on long-horizon tasks still represents a major challenge -- the longer the task is, the more likely it is that some stage will fail. Can humans help the robot to continuously improve its long-horizon task performance through"},"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":"2403.12910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-19T17:08:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2291a298c101471f80142069a6fdd69b5c4c38200c17c5b448d545136411c7d","abstract_canon_sha256":"0c82f68693df18cc31afda6eeb6ada7ff85131c442f5803f29565c363cb804e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:09.436250Z","signature_b64":"PRTE6RU+3bSKNpfEdE1nz2Re//UUJzIHLkET9Bbnk2qcK4rLll918WjO42XZsuaXvQIDnlt6Ex91+U2BZbrJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22dd972bc4a4474f2dfc6b78ed78b9e3464f4fa3a31b122fad0f0c745f7f1a10","last_reissued_at":"2026-07-05T07:58:09.435771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:09.435771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Archit Sharma, Chelsea Finn, Jianlan Luo, Karl Pertsch, Lucy Xiaoyang Shi, Sergey Levine, Tony Z. Zhao, Zheyuan Hu","submitted_at":"2024-03-19T17:08:24Z","abstract_excerpt":"Hierarchical policies that combine language and low-level control have been shown to perform impressively long-horizon robotic tasks, by leveraging either zero-shot high-level planners like pretrained language and vision-language models (LLMs/VLMs) or models trained on annotated robotic demonstrations. However, for complex and dexterous skills, attaining high success rates on long-horizon tasks still represents a major challenge -- the longer the task is, the more likely it is that some stage will fail. Can humans help the robot to continuously improve its long-horizon task performance through"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12910","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/2403.12910/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":"2403.12910","created_at":"2026-07-05T07:58:09.435826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12910v1","created_at":"2026-07-05T07:58:09.435826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12910","created_at":"2026-07-05T07:58:09.435826+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELOZOK6EURDU","created_at":"2026-07-05T07:58:09.435826+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELOZOK6EURDU6LP4","created_at":"2026-07-05T07:58:09.435826+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELOZOK6E","created_at":"2026-07-05T07:58:09.435826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12475","citing_title":"Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12299","citing_title":"Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08495","citing_title":"EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06461","citing_title":"Flow-based Policy Adaptation without Policy Updates","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31958","citing_title":"Adapting Generalist Robot Policies with Semantic Reinforcement Learning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":53,"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":71,"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":83,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12514","citing_title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":155,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08434","citing_title":"Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08434","citing_title":"Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09410","citing_title":"RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models","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":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N","json":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N.json","graph_json":"https://pith.science/api/pith-number/ELOZOK6EURDU6LP4NN4O26FZ4N/graph.json","events_json":"https://pith.science/api/pith-number/ELOZOK6EURDU6LP4NN4O26FZ4N/events.json","paper":"https://pith.science/paper/ELOZOK6E"},"agent_actions":{"view_html":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N","download_json":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N.json","view_paper":"https://pith.science/paper/ELOZOK6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12910&json=true","fetch_graph":"https://pith.science/api/pith-number/ELOZOK6EURDU6LP4NN4O26FZ4N/graph.json","fetch_events":"https://pith.science/api/pith-number/ELOZOK6EURDU6LP4NN4O26FZ4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N/action/storage_attestation","attest_author":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N/action/author_attestation","sign_citation":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N/action/citation_signature","submit_replication":"https://pith.science/pith/ELOZOK6EURDU6LP4NN4O26FZ4N/action/replication_record"}},"created_at":"2026-07-05T07:58:09.435826+00:00","updated_at":"2026-07-05T07:58:09.435826+00:00"}