{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:75QNKSPVS33ZTBIPAHXU5VBEZQ","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":"c0bd9f185f31d217586b0371c5a420bd649dfd5b4975ec5c8c2acb98ff7aaaaf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T17:32:11Z","title_canon_sha256":"6c1ac77748bc0962345ca9b3db70c8743a23cf1b0dd295463f60c8ea37fd69a5"},"schema_version":"1.0","source":{"id":"2210.05639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05639","created_at":"2026-07-05T05:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05639v2","created_at":"2026-07-05T05:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05639","created_at":"2026-07-05T05:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"75QNKSPVS33Z","created_at":"2026-07-05T05:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"75QNKSPVS33ZTBIP","created_at":"2026-07-05T05:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"75QNKSPV","created_at":"2026-07-05T05:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:5b508c9587c95f9b7335c9ea6eb536e27b9cc4b2a4a9f16996dd5cc4085bd655","target":"graph","created_at":"2026-07-05T05:06:15Z","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/2210.05639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which were designed using a combination of mathematical derivations, intuitions, and experimentation. Such an approach of creating algorithms manually is limited by human understanding and ingenuity. In contrast, meta-learning provides a toolkit for automatic machine learning method optimisation, potentially addressing this flaw. However, black-box approaches which attempt to discover RL algorithms with minimal prior structu","authors_text":"Alistair Letcher, Chris Lu, Christian Schroeder de Witt, Jakob Foerster, Jakub Grudzien Kuba, Luke Metz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T17:32:11Z","title":"Discovered Policy Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05639","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":"sha256:6ba690d061ad29afc859e148b378aa2eeac0bcc9147ed27f44dcfc1812c5b6e4","target":"record","created_at":"2026-07-05T05:06:15Z","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":"c0bd9f185f31d217586b0371c5a420bd649dfd5b4975ec5c8c2acb98ff7aaaaf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T17:32:11Z","title_canon_sha256":"6c1ac77748bc0962345ca9b3db70c8743a23cf1b0dd295463f60c8ea37fd69a5"},"schema_version":"1.0","source":{"id":"2210.05639","kind":"arxiv","version":2}},"canonical_sha256":"ff60d549f596f799850f01ef4ed424cc24c42870c54574a38129eace44edb722","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff60d549f596f799850f01ef4ed424cc24c42870c54574a38129eace44edb722","first_computed_at":"2026-07-05T05:06:15.701055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:15.701055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"28Er9If6aWLs59SAxxHeGRIRawFOjzf+ZXHTCfTQfBaUTAglH9/ycupEKoVEoNJYFyQWgX/TIUo0JE+pXtaCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:15.701541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ba690d061ad29afc859e148b378aa2eeac0bcc9147ed27f44dcfc1812c5b6e4","sha256:5b508c9587c95f9b7335c9ea6eb536e27b9cc4b2a4a9f16996dd5cc4085bd655"],"state_sha256":"e97d70686aefdeb7d61325a333c5eef2bed60795e4162ed96fce67bcf4837cf7"}