{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DNMBD3WLJOJIYSGPEPAUHRQL3R","short_pith_number":"pith:DNMBD3WL","schema_version":"1.0","canonical_sha256":"1b5811eecb4b928c48cf23c143c60bdc73cb8b8ac96c0c0a16c76bf67f6024dd","source":{"kind":"arxiv","id":"2406.01967","version":1},"attestation_state":"computed","paper":{"title":"DrEureka: Language Model Guided Sim-To-Real Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dinesh Jayaraman, Hung-Ju Wang, Linxi Fan, Osbert Bastani, Sam Wang, William Liang, Yecheng Jason Ma, Yuke Zhu","submitted_at":"2024-06-04T04:53:05Z","abstract_excerpt":"Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulation physics parameters, rendering the process slow and human-labor intensive. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our LLM-guided sim-to-real approach, DrEureka, requires only the physics simulation for the target task and automatically constructs suitable reward functions and"},"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":"2406.01967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-04T04:53:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4f743aae46120c7272ed2110a31c9841b60c99e933033eab51ccfec73316cdd5","abstract_canon_sha256":"698cf2cf88a4364914a550a674d661a94d064f626acdfb941fa6d5233c615678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:12.325510Z","signature_b64":"AQXD96in6Zmoys03kjdlQJ6QAzuNurYMwW//NNhMG8yEbKIVi7JShdc4b9xjHuAyAQO51PVE4zW7fVke8b03AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b5811eecb4b928c48cf23c143c60bdc73cb8b8ac96c0c0a16c76bf67f6024dd","last_reissued_at":"2026-07-05T08:27:12.324912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:12.324912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrEureka: Language Model Guided Sim-To-Real Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dinesh Jayaraman, Hung-Ju Wang, Linxi Fan, Osbert Bastani, Sam Wang, William Liang, Yecheng Jason Ma, Yuke Zhu","submitted_at":"2024-06-04T04:53:05Z","abstract_excerpt":"Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulation physics parameters, rendering the process slow and human-labor intensive. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our LLM-guided sim-to-real approach, DrEureka, requires only the physics simulation for the target task and automatically constructs suitable reward functions and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01967","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/2406.01967/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":"2406.01967","created_at":"2026-07-05T08:27:12.325005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01967v1","created_at":"2026-07-05T08:27:12.325005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01967","created_at":"2026-07-05T08:27:12.325005+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNMBD3WLJOJI","created_at":"2026-07-05T08:27:12.325005+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNMBD3WLJOJIYSGP","created_at":"2026-07-05T08:27:12.325005+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNMBD3WL","created_at":"2026-07-05T08:27:12.325005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19419","citing_title":"Playful Agentic Robot Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08315","citing_title":"Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00244","citing_title":"Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R","json":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R.json","graph_json":"https://pith.science/api/pith-number/DNMBD3WLJOJIYSGPEPAUHRQL3R/graph.json","events_json":"https://pith.science/api/pith-number/DNMBD3WLJOJIYSGPEPAUHRQL3R/events.json","paper":"https://pith.science/paper/DNMBD3WL"},"agent_actions":{"view_html":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R","download_json":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R.json","view_paper":"https://pith.science/paper/DNMBD3WL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01967&json=true","fetch_graph":"https://pith.science/api/pith-number/DNMBD3WLJOJIYSGPEPAUHRQL3R/graph.json","fetch_events":"https://pith.science/api/pith-number/DNMBD3WLJOJIYSGPEPAUHRQL3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R/action/storage_attestation","attest_author":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R/action/author_attestation","sign_citation":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R/action/citation_signature","submit_replication":"https://pith.science/pith/DNMBD3WLJOJIYSGPEPAUHRQL3R/action/replication_record"}},"created_at":"2026-07-05T08:27:12.325005+00:00","updated_at":"2026-07-05T08:27:12.325005+00:00"}