{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FAVUWT2GGHSCQMQK6I3FPQOQ6D","short_pith_number":"pith:FAVUWT2G","schema_version":"1.0","canonical_sha256":"282b4b4f4631e428320af23657c1d0f0f8a0d9824ee05c919581742a2f277ca9","source":{"kind":"arxiv","id":"2306.09205","version":2},"attestation_state":"computed","paper":{"title":"Reward-Free Curricula for Training Robust World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ingmar Posner, Marc Rigter, Minqi Jiang","submitted_at":"2023-06-15T15:40:04Z","abstract_excerpt":"There has been a recent surge of interest in developing generally-capable agents that can adapt to new tasks without additional training in the environment. Learning world models from reward-free exploration is a promising approach, and enables policies to be trained using imagined experience for new tasks. However, achieving a general agent requires robustness across different environments. In this work, we address the novel problem of generating curricula in the reward-free setting to train robust world models. We consider robustness in terms of minimax regret over all environment instantiat"},"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":"2306.09205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:40:04Z","cross_cats_sorted":[],"title_canon_sha256":"760eacc939a282a853bc7a89ace29d4eb9fae79900e16a603e8f66dd39871edc","abstract_canon_sha256":"5685526449460bfee7bf96e662d01c14e51ca53f39af481573f0dd5c20065bdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:51.753461Z","signature_b64":"GTp+ChgaW0kUq8JBA9d6QQeEW7OZ5uo6CJVdrDtlhr8HY+V6mZFDTLtx7RMjxMaM/9hv4Zt3/PPWwyu3iahBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282b4b4f4631e428320af23657c1d0f0f8a0d9824ee05c919581742a2f277ca9","last_reissued_at":"2026-07-05T07:36:51.752988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:51.752988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Free Curricula for Training Robust World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ingmar Posner, Marc Rigter, Minqi Jiang","submitted_at":"2023-06-15T15:40:04Z","abstract_excerpt":"There has been a recent surge of interest in developing generally-capable agents that can adapt to new tasks without additional training in the environment. Learning world models from reward-free exploration is a promising approach, and enables policies to be trained using imagined experience for new tasks. However, achieving a general agent requires robustness across different environments. In this work, we address the novel problem of generating curricula in the reward-free setting to train robust world models. We consider robustness in terms of minimax regret over all environment instantiat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09205","kind":"arxiv","version":2},"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/2306.09205/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":"2306.09205","created_at":"2026-07-05T07:36:51.753043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09205v2","created_at":"2026-07-05T07:36:51.753043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09205","created_at":"2026-07-05T07:36:51.753043+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAVUWT2GGHSC","created_at":"2026-07-05T07:36:51.753043+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAVUWT2GGHSCQMQK","created_at":"2026-07-05T07:36:51.753043+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAVUWT2G","created_at":"2026-07-05T07:36:51.753043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10425","citing_title":"Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D","json":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D.json","graph_json":"https://pith.science/api/pith-number/FAVUWT2GGHSCQMQK6I3FPQOQ6D/graph.json","events_json":"https://pith.science/api/pith-number/FAVUWT2GGHSCQMQK6I3FPQOQ6D/events.json","paper":"https://pith.science/paper/FAVUWT2G"},"agent_actions":{"view_html":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D","download_json":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D.json","view_paper":"https://pith.science/paper/FAVUWT2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09205&json=true","fetch_graph":"https://pith.science/api/pith-number/FAVUWT2GGHSCQMQK6I3FPQOQ6D/graph.json","fetch_events":"https://pith.science/api/pith-number/FAVUWT2GGHSCQMQK6I3FPQOQ6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D/action/storage_attestation","attest_author":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D/action/author_attestation","sign_citation":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D/action/citation_signature","submit_replication":"https://pith.science/pith/FAVUWT2GGHSCQMQK6I3FPQOQ6D/action/replication_record"}},"created_at":"2026-07-05T07:36:51.753043+00:00","updated_at":"2026-07-05T07:36:51.753043+00:00"}