{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K75SK7UNSZMUD4PEGKMIEXW3PY","short_pith_number":"pith:K75SK7UN","schema_version":"1.0","canonical_sha256":"57fb257e8d965941f1e43298825edb7e20aa97daf25b98c12dd1e0c498f51477","source":{"kind":"arxiv","id":"2411.01775","version":1},"attestation_state":"computed","paper":{"title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","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, Osbert Bastani, Sam Wang, William Liang, Yecheng Jason Ma","submitted_at":"2024-11-04T03:54:00Z","abstract_excerpt":"Recent work has demonstrated that a promising strategy for teaching robots a wide range of complex skills is by training them on a curriculum of progressively more challenging environments. However, developing an effective curriculum of environment distributions currently requires significant expertise, which must be repeated for every new domain. Our key insight is that environments are often naturally represented as code. Thus, we probe whether effective environment curriculum design can be achieved and automated via code generation by large language models (LLM). In this paper, we introduce"},"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":"2411.01775","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-04T03:54:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a7f4265efc91c9c40a3aaa63007e6e416d98456811ea4d19270aea9ba7da06f3","abstract_canon_sha256":"6b546304682276d531a2a9705af487e3461973168d7dfffa639c615b1ca01d89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:36.064649Z","signature_b64":"FLSgXLfLkqDH2kHE97lRVXw+QKfSzt52xjGTDV8Vxo+Bewml0ccCCcz3PJLa2pPWDHfFpt6SlTCnf35lb6sXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57fb257e8d965941f1e43298825edb7e20aa97daf25b98c12dd1e0c498f51477","last_reissued_at":"2026-07-05T09:30:36.064164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:36.064164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","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, Osbert Bastani, Sam Wang, William Liang, Yecheng Jason Ma","submitted_at":"2024-11-04T03:54:00Z","abstract_excerpt":"Recent work has demonstrated that a promising strategy for teaching robots a wide range of complex skills is by training them on a curriculum of progressively more challenging environments. However, developing an effective curriculum of environment distributions currently requires significant expertise, which must be repeated for every new domain. Our key insight is that environments are often naturally represented as code. Thus, we probe whether effective environment curriculum design can be achieved and automated via code generation by large language models (LLM). In this paper, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01775","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/2411.01775/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":"2411.01775","created_at":"2026-07-05T09:30:36.064226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01775v1","created_at":"2026-07-05T09:30:36.064226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01775","created_at":"2026-07-05T09:30:36.064226+00:00"},{"alias_kind":"pith_short_12","alias_value":"K75SK7UNSZMU","created_at":"2026-07-05T09:30:36.064226+00:00"},{"alias_kind":"pith_short_16","alias_value":"K75SK7UNSZMUD4PE","created_at":"2026-07-05T09:30:36.064226+00:00"},{"alias_kind":"pith_short_8","alias_value":"K75SK7UN","created_at":"2026-07-05T09:30:36.064226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20324","citing_title":"A Model-Driven Approach for Developing Families of Reinforcement Learning Environments","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY","json":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY.json","graph_json":"https://pith.science/api/pith-number/K75SK7UNSZMUD4PEGKMIEXW3PY/graph.json","events_json":"https://pith.science/api/pith-number/K75SK7UNSZMUD4PEGKMIEXW3PY/events.json","paper":"https://pith.science/paper/K75SK7UN"},"agent_actions":{"view_html":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY","download_json":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY.json","view_paper":"https://pith.science/paper/K75SK7UN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01775&json=true","fetch_graph":"https://pith.science/api/pith-number/K75SK7UNSZMUD4PEGKMIEXW3PY/graph.json","fetch_events":"https://pith.science/api/pith-number/K75SK7UNSZMUD4PEGKMIEXW3PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY/action/storage_attestation","attest_author":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY/action/author_attestation","sign_citation":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY/action/citation_signature","submit_replication":"https://pith.science/pith/K75SK7UNSZMUD4PEGKMIEXW3PY/action/replication_record"}},"created_at":"2026-07-05T09:30:36.064226+00:00","updated_at":"2026-07-05T09:30:36.064226+00:00"}