{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JJYN4G75MUVJAPSFTT6WFNXZ3K","short_pith_number":"pith:JJYN4G75","schema_version":"1.0","canonical_sha256":"4a70de1bfd652a903e459cfd62b6f9dab8e9f565ff82f273812d2c4609d4d949","source":{"kind":"arxiv","id":"2409.14674","version":1},"attestation_state":"computed","paper":{"title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Jayjun Lee, Joyce Chai, Nima Fazeli, Yinpei Dai","submitted_at":"2024-09-23T02:50:33Z","abstract_excerpt":"Developing robust and correctable visuomotor policies for robotic manipulation is challenging due to the lack of self-recovery mechanisms from failures and the limitations of simple language instructions in guiding robot actions. To address these issues, we propose a scalable data generation pipeline that automatically augments expert demonstrations with failure recovery trajectories and fine-grained language annotations for training. We then introduce Rich languAge-guided failure reCovERy (RACER), a supervisor-actor framework, which combines failure recovery data with rich language descriptio"},"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":"2409.14674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-23T02:50:33Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"683873e4b7904328a7a0b608ec47d3d4a7cb7558c00b7f9f8482c6ede74bec7f","abstract_canon_sha256":"825a625b98ee73157e96238f816ae4fec25506cda6c5b0a530ba36a6e19c32ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:20.041272Z","signature_b64":"u9+5Abxvg2uSHQzsSeofovNY28rwnwznDHsSGYSM2oG2TLiU9Mr8GxYD0xwLwEIHHL3qsxiTxFyWJvcep0DwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a70de1bfd652a903e459cfd62b6f9dab8e9f565ff82f273812d2c4609d4d949","last_reissued_at":"2026-07-05T09:10:20.040795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:20.040795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Jayjun Lee, Joyce Chai, Nima Fazeli, Yinpei Dai","submitted_at":"2024-09-23T02:50:33Z","abstract_excerpt":"Developing robust and correctable visuomotor policies for robotic manipulation is challenging due to the lack of self-recovery mechanisms from failures and the limitations of simple language instructions in guiding robot actions. To address these issues, we propose a scalable data generation pipeline that automatically augments expert demonstrations with failure recovery trajectories and fine-grained language annotations for training. We then introduce Rich languAge-guided failure reCovERy (RACER), a supervisor-actor framework, which combines failure recovery data with rich language descriptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14674","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/2409.14674/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":"2409.14674","created_at":"2026-07-05T09:10:20.040852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14674v1","created_at":"2026-07-05T09:10:20.040852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14674","created_at":"2026-07-05T09:10:20.040852+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJYN4G75MUVJ","created_at":"2026-07-05T09:10:20.040852+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJYN4G75MUVJAPSF","created_at":"2026-07-05T09:10:20.040852+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJYN4G75","created_at":"2026-07-05T09:10:20.040852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09630","citing_title":"ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07723","citing_title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23847","citing_title":"Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger Insertion","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17666","citing_title":"Robust and Resilient Soft Robotic Object Insertion with Compliance-Enabled Contact Formation and Failure Recovery","ref_index":12,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K","json":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K.json","graph_json":"https://pith.science/api/pith-number/JJYN4G75MUVJAPSFTT6WFNXZ3K/graph.json","events_json":"https://pith.science/api/pith-number/JJYN4G75MUVJAPSFTT6WFNXZ3K/events.json","paper":"https://pith.science/paper/JJYN4G75"},"agent_actions":{"view_html":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K","download_json":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K.json","view_paper":"https://pith.science/paper/JJYN4G75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14674&json=true","fetch_graph":"https://pith.science/api/pith-number/JJYN4G75MUVJAPSFTT6WFNXZ3K/graph.json","fetch_events":"https://pith.science/api/pith-number/JJYN4G75MUVJAPSFTT6WFNXZ3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K/action/storage_attestation","attest_author":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K/action/author_attestation","sign_citation":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K/action/citation_signature","submit_replication":"https://pith.science/pith/JJYN4G75MUVJAPSFTT6WFNXZ3K/action/replication_record"}},"created_at":"2026-07-05T09:10:20.040852+00:00","updated_at":"2026-07-05T09:10:20.040852+00:00"}