{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SUVGANQJHREOKOWIN4EUA4KSNX","short_pith_number":"pith:SUVGANQJ","canonical_record":{"source":{"id":"2402.12284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T16:51:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f6cd65d2eea1c24952bb68fa42d07fcfc1af405d26e3377c90fc50def9e2b86","abstract_canon_sha256":"0951ef7ce0e86b1dac85cb01ccd96a9c617cf2ef7d234ad323e882cf93b30e87"},"schema_version":"1.0"},"canonical_sha256":"952a6036093c48e53ac86f094071526dea29dd1e735096603470218e26d41f4a","source":{"kind":"arxiv","id":"2402.12284","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12284","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12284v2","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12284","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"SUVGANQJHREO","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"SUVGANQJHREOKOWI","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"SUVGANQJ","created_at":"2026-07-05T08:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SUVGANQJHREOKOWIN4EUA4KSNX","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T16:51:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f6cd65d2eea1c24952bb68fa42d07fcfc1af405d26e3377c90fc50def9e2b86","abstract_canon_sha256":"0951ef7ce0e86b1dac85cb01ccd96a9c617cf2ef7d234ad323e882cf93b30e87"},"schema_version":"1.0"},"canonical_sha256":"952a6036093c48e53ac86f094071526dea29dd1e735096603470218e26d41f4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:59.697527Z","signature_b64":"NvYQKZeCGb4ckNmo9I6Q6XlqmA+4t/29tnlD+0nhcd7nFAea8BwVK5AhM8R1gPcgI7SS0H5mC4pDQgKltBa5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"952a6036093c48e53ac86f094071526dea29dd1e735096603470218e26d41f4a","last_reissued_at":"2026-07-05T08:28:59.697002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:59.697002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12284","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RgLaIzrcAObQdDEbbF9C6LXjcNgY8L7eEmSXmEQ5Hn5+RrohFkXXe3fRJQ2YpaV1xsAE3Cjj4gguEAQx/U6dBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:49:01.620869Z"},"content_sha256":"7e13091afa5fdc53bf30499fc0d51d637e192c1c0344bf94671f38e6bcf8327f","schema_version":"1.0","event_id":"sha256:7e13091afa5fdc53bf30499fc0d51d637e192c1c0344bf94671f38e6bcf8327f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SUVGANQJHREOKOWIN4EUA4KSNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refining Minimax Regret for Unsupervised Environment Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jakob Foerster, Mattie Fellows, Michael Beukman, Michael Dennis, Michael Matthews, Minqi Jiang, Samuel Coward","submitted_at":"2024-02-19T16:51:29Z","abstract_excerpt":"In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises some objective. Regret is a commonly used objective that theoretically results in a minimax regret (MMR) policy with desirable robustness guarantees; in particular, the agent's maximum regret is bounded. However, once the agent reaches this regret bound on all levels, the adversary will only sample levels where regret cannot be further reduced. Although there are possible performance improvements to be made outside of these regret-maximis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12284","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/2402.12284/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FrLga+Qd8maoe5FUar92CFkGRAYpo2GzdPxAH4TozlpCJnyFrI4tsDOc9srTW9CcOrCCVY9oU4PwqrPKiq5pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:49:01.621522Z"},"content_sha256":"3753248c0f596eea006091bd7f3ff396ce60c885c50565ed27d639eeb1b05a02","schema_version":"1.0","event_id":"sha256:3753248c0f596eea006091bd7f3ff396ce60c885c50565ed27d639eeb1b05a02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SUVGANQJHREOKOWIN4EUA4KSNX/bundle.json","state_url":"https://pith.science/pith/SUVGANQJHREOKOWIN4EUA4KSNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SUVGANQJHREOKOWIN4EUA4KSNX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T23:49:01Z","links":{"resolver":"https://pith.science/pith/SUVGANQJHREOKOWIN4EUA4KSNX","bundle":"https://pith.science/pith/SUVGANQJHREOKOWIN4EUA4KSNX/bundle.json","state":"https://pith.science/pith/SUVGANQJHREOKOWIN4EUA4KSNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SUVGANQJHREOKOWIN4EUA4KSNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SUVGANQJHREOKOWIN4EUA4KSNX","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":"0951ef7ce0e86b1dac85cb01ccd96a9c617cf2ef7d234ad323e882cf93b30e87","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T16:51:29Z","title_canon_sha256":"3f6cd65d2eea1c24952bb68fa42d07fcfc1af405d26e3377c90fc50def9e2b86"},"schema_version":"1.0","source":{"id":"2402.12284","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12284","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12284v2","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12284","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"SUVGANQJHREO","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"SUVGANQJHREOKOWI","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"SUVGANQJ","created_at":"2026-07-05T08:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:3753248c0f596eea006091bd7f3ff396ce60c885c50565ed27d639eeb1b05a02","target":"graph","created_at":"2026-07-05T08:28:59Z","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/2402.12284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises some objective. Regret is a commonly used objective that theoretically results in a minimax regret (MMR) policy with desirable robustness guarantees; in particular, the agent's maximum regret is bounded. However, once the agent reaches this regret bound on all levels, the adversary will only sample levels where regret cannot be further reduced. Although there are possible performance improvements to be made outside of these regret-maximis","authors_text":"Jakob Foerster, Mattie Fellows, Michael Beukman, Michael Dennis, Michael Matthews, Minqi Jiang, Samuel Coward","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T16:51:29Z","title":"Refining Minimax Regret for Unsupervised Environment Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12284","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":"sha256:7e13091afa5fdc53bf30499fc0d51d637e192c1c0344bf94671f38e6bcf8327f","target":"record","created_at":"2026-07-05T08:28:59Z","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":"0951ef7ce0e86b1dac85cb01ccd96a9c617cf2ef7d234ad323e882cf93b30e87","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T16:51:29Z","title_canon_sha256":"3f6cd65d2eea1c24952bb68fa42d07fcfc1af405d26e3377c90fc50def9e2b86"},"schema_version":"1.0","source":{"id":"2402.12284","kind":"arxiv","version":2}},"canonical_sha256":"952a6036093c48e53ac86f094071526dea29dd1e735096603470218e26d41f4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"952a6036093c48e53ac86f094071526dea29dd1e735096603470218e26d41f4a","first_computed_at":"2026-07-05T08:28:59.697002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:59.697002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NvYQKZeCGb4ckNmo9I6Q6XlqmA+4t/29tnlD+0nhcd7nFAea8BwVK5AhM8R1gPcgI7SS0H5mC4pDQgKltBa5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:59.697527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12284","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e13091afa5fdc53bf30499fc0d51d637e192c1c0344bf94671f38e6bcf8327f","sha256:3753248c0f596eea006091bd7f3ff396ce60c885c50565ed27d639eeb1b05a02"],"state_sha256":"d75f2b54675d73e4bb252e548111d298d388a028c76c3dc16a52901de6ea05c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRlERgy3UxFC/Heef+3zl4an0954BJAo15xI4XHhurGNfspkHgjhgoZF+TOY1nICw9dheIXM8KZQUw5ZHvqSBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:49:01.627782Z","bundle_sha256":"9da272e513e0ec891f2632261070b79e66fb9f2758c87d38373364dfa772bbf3"}}