{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MFFSB25P7RKMBVBSXWPK46TXSJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"140ea92c156d94e03ace2b84fd8ff4c3a2f9f90c88c80724eeb4a05551b3a69e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T15:42:56Z","title_canon_sha256":"9e5413cde16b37d9139220662e6d024d680c5c5eb72fe13d5cb0b2c99d27dca5"},"schema_version":"1.0","source":{"id":"2308.10797","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10797","created_at":"2026-07-05T06:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10797v2","created_at":"2026-07-05T06:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10797","created_at":"2026-07-05T06:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"MFFSB25P7RKM","created_at":"2026-07-05T06:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"MFFSB25P7RKMBVBS","created_at":"2026-07-05T06:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"MFFSB25P","created_at":"2026-07-05T06:43:26Z"}],"graph_snapshots":[{"event_id":"sha256:fe20a0d061f2ddb35672eb70687cb411553de4670c74b3c30404a73bf6ebc351","target":"graph","created_at":"2026-07-05T06:43:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.10797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key challenge in training generally-capable agents is the design of training tasks that facilitate broad generalization and robustness to environment variations. This challenge motivates the problem setting of Unsupervised Environment Design (UED), whereby a student agent trains on an adaptive distribution of tasks proposed by a teacher agent. A pioneering approach for UED is PAIRED, which uses reinforcement learning (RL) to train a teacher policy to design tasks from scratch, making it possible to directly generate tasks that are adapted to the agent's current capabilities. Despite its stro","authors_text":"Eugene Vinitsky, Ishita Mediratta, Jack Parker-Holder, Michael Dennis, Minqi Jiang, Tim Rockt\\\"aschel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T15:42:56Z","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10797","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:398f48cd02f6dba92f94e093a413e5ed236baefe7ac6cc870c16376560c84752","target":"record","created_at":"2026-07-05T06:43:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"140ea92c156d94e03ace2b84fd8ff4c3a2f9f90c88c80724eeb4a05551b3a69e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T15:42:56Z","title_canon_sha256":"9e5413cde16b37d9139220662e6d024d680c5c5eb72fe13d5cb0b2c99d27dca5"},"schema_version":"1.0","source":{"id":"2308.10797","kind":"arxiv","version":2}},"canonical_sha256":"614b20ebaffc54c0d432bd9eae7a7792749d27f225fd961336a147e4d32fc19b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"614b20ebaffc54c0d432bd9eae7a7792749d27f225fd961336a147e4d32fc19b","first_computed_at":"2026-07-05T06:43:26.455827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:26.455827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lxNjB8mjHNquzdFnrOtEDjnsAG07vT6AltPsNax9e58wrf3aBEjavmCGK8t8c0JeQ4fZRBaI72YiPr+1og5aCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:26.456420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10797","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:398f48cd02f6dba92f94e093a413e5ed236baefe7ac6cc870c16376560c84752","sha256:fe20a0d061f2ddb35672eb70687cb411553de4670c74b3c30404a73bf6ebc351"],"state_sha256":"f37872457cbea0f13ca9c9ccc556dc7602e6a353aad4766d3d3310e1ef8f3ca9"}