{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:75QNKSPVS33ZTBIPAHXU5VBEZQ","short_pith_number":"pith:75QNKSPV","canonical_record":{"source":{"id":"2210.05639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T17:32:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c1ac77748bc0962345ca9b3db70c8743a23cf1b0dd295463f60c8ea37fd69a5","abstract_canon_sha256":"c0bd9f185f31d217586b0371c5a420bd649dfd5b4975ec5c8c2acb98ff7aaaaf"},"schema_version":"1.0"},"canonical_sha256":"ff60d549f596f799850f01ef4ed424cc24c42870c54574a38129eace44edb722","source":{"kind":"arxiv","id":"2210.05639","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:75QNKSPVS33ZTBIPAHXU5VBEZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T17:32:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c1ac77748bc0962345ca9b3db70c8743a23cf1b0dd295463f60c8ea37fd69a5","abstract_canon_sha256":"c0bd9f185f31d217586b0371c5a420bd649dfd5b4975ec5c8c2acb98ff7aaaaf"},"schema_version":"1.0"},"canonical_sha256":"ff60d549f596f799850f01ef4ed424cc24c42870c54574a38129eace44edb722","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:15.701541Z","signature_b64":"28Er9If6aWLs59SAxxHeGRIRawFOjzf+ZXHTCfTQfBaUTAglH9/ycupEKoVEoNJYFyQWgX/TIUo0JE+pXtaCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff60d549f596f799850f01ef4ed424cc24c42870c54574a38129eace44edb722","last_reissued_at":"2026-07-05T05:06:15.701055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:15.701055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05639","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":"2026-07-05T05:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zjGwZ3IFeCLUSYZkYjDiaSRj2q2U9mJ1+IytOx0OsiiyP0XksFzriSCchV/25TKECW3zXi4aV6ZcZJuYHNPmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:34:20.528017Z"},"content_sha256":"6ba690d061ad29afc859e148b378aa2eeac0bcc9147ed27f44dcfc1812c5b6e4","schema_version":"1.0","event_id":"sha256:6ba690d061ad29afc859e148b378aa2eeac0bcc9147ed27f44dcfc1812c5b6e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:75QNKSPVS33ZTBIPAHXU5VBEZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovered Policy Optimisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alistair Letcher, Chris Lu, Christian Schroeder de Witt, Jakob Foerster, Jakub Grudzien Kuba, Luke Metz","submitted_at":"2022-10-11T17:32:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05639","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/2210.05639/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":"2026-07-05T05:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S/A3jr9lBCuSgl+9IgEP6Q1VuSzjfiQ6pQvM1V//wQ/WCfTNbbfscFiEsXJ6kehek5Hr1RJRf0dWJ2WE/uSSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:34:20.528568Z"},"content_sha256":"5b508c9587c95f9b7335c9ea6eb536e27b9cc4b2a4a9f16996dd5cc4085bd655","schema_version":"1.0","event_id":"sha256:5b508c9587c95f9b7335c9ea6eb536e27b9cc4b2a4a9f16996dd5cc4085bd655"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ/bundle.json","state_url":"https://pith.science/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ/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":"2026-08-11T05:34:20Z","links":{"resolver":"https://pith.science/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ","bundle":"https://pith.science/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ/bundle.json","state":"https://pith.science/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75QNKSPVS33ZTBIPAHXU5VBEZQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQdeKh7MSuTQQNmmTqFkNjWQFtf1RUqb69EYKHp7Dg61UzQ4lJkYNgKRJig2AhRLA1g2I8OSv693EL7CPJQ+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:34:20.534459Z","bundle_sha256":"985107f9990c8d4eef7e258bee65cdc3165f86f0f6932b9390d52717093c4c85"}}