{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FMD4H45OD6F45TULUVTU2GTSQL","short_pith_number":"pith:FMD4H45O","canonical_record":{"source":{"id":"2310.02782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T12:52:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf5197ae70bd11b44226f53840c32175c146194a99d964d547ed6840d0d426af","abstract_canon_sha256":"36e6a255b551a38bb191bb1e6366efa5c14adf733011c02a157038835ade2026"},"schema_version":"1.0"},"canonical_sha256":"2b07c3f3ae1f8bcece8ba5674d1a7282f1f81bca4b04fd2da7becc909de88dbb","source":{"kind":"arxiv","id":"2310.02782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02782","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02782v1","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02782","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"pith_short_12","alias_value":"FMD4H45OD6F4","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"pith_short_16","alias_value":"FMD4H45OD6F45TUL","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"pith_short_8","alias_value":"FMD4H45O","created_at":"2026-07-05T06:57:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FMD4H45OD6F45TULUVTU2GTSQL","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T12:52:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf5197ae70bd11b44226f53840c32175c146194a99d964d547ed6840d0d426af","abstract_canon_sha256":"36e6a255b551a38bb191bb1e6366efa5c14adf733011c02a157038835ade2026"},"schema_version":"1.0"},"canonical_sha256":"2b07c3f3ae1f8bcece8ba5674d1a7282f1f81bca4b04fd2da7becc909de88dbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:13.877221Z","signature_b64":"5BTtsXwdiyrQDFGUq+LOfpK71WEJ+oPqzxpyOQlQu66SKvEiRqQ0TAHhkzoE5bzTgEYmkrJq1FUoeeQhdgrCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b07c3f3ae1f8bcece8ba5674d1a7282f1f81bca4b04fd2da7becc909de88dbb","last_reissued_at":"2026-07-05T06:57:13.876680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:13.876680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02782","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:57:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFyE0HYHLQ2+bjW6Uuo4w81mOSXO1b4n5DFVWFmQtpYb7VaZg6qUdvoh076afz3dsj9mAlmFf848DKq/042MCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:15:52.214437Z"},"content_sha256":"0e7610aeccd10e626ae746c9499850aa18f79c6316597f02a2921b65244c02ac","schema_version":"1.0","event_id":"sha256:0e7610aeccd10e626ae746c9499850aa18f79c6316597f02a2921b65244c02ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FMD4H45OD6F45TULUVTU2GTSQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Lu, Gregory Farquhar, Jack Parker-Holder, Jakob Nicolaus Foerster, Matthew Thomas Jackson, Minqi Jiang, Risto Vuorio, Shimon Whiteson","submitted_at":"2023-10-04T12:52:56Z","abstract_excerpt":"The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of discovering algorithms that can perform well on a wide range of RL tasks. Despite impressive initial results from algorithms such as Learned Policy Gradient (LPG), there remains a generalization gap when these algorithms are applied to unseen environments. In this work, we examine how characteristics of the meta-training distribution impact the generalization perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02782","kind":"arxiv","version":1},"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/2310.02782/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":"2026-07-05T06:57:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+VqBxIa0JFSZxHN74JudcVUaJTW/QBS4rR51fLDGtu4tXiXo55RggEac5aILBZGjYMnRULtxMJeOZyrOJ3tDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:15:52.215082Z"},"content_sha256":"9386f2b63ccc492def04f05d0416abfa63ba49765f42186f19bbebf9345c33a6","schema_version":"1.0","event_id":"sha256:9386f2b63ccc492def04f05d0416abfa63ba49765f42186f19bbebf9345c33a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMD4H45OD6F45TULUVTU2GTSQL/bundle.json","state_url":"https://pith.science/pith/FMD4H45OD6F45TULUVTU2GTSQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMD4H45OD6F45TULUVTU2GTSQL/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":"2026-08-08T10:15:52Z","links":{"resolver":"https://pith.science/pith/FMD4H45OD6F45TULUVTU2GTSQL","bundle":"https://pith.science/pith/FMD4H45OD6F45TULUVTU2GTSQL/bundle.json","state":"https://pith.science/pith/FMD4H45OD6F45TULUVTU2GTSQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMD4H45OD6F45TULUVTU2GTSQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FMD4H45OD6F45TULUVTU2GTSQL","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":"36e6a255b551a38bb191bb1e6366efa5c14adf733011c02a157038835ade2026","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T12:52:56Z","title_canon_sha256":"bf5197ae70bd11b44226f53840c32175c146194a99d964d547ed6840d0d426af"},"schema_version":"1.0","source":{"id":"2310.02782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02782","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02782v1","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02782","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"pith_short_12","alias_value":"FMD4H45OD6F4","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"pith_short_16","alias_value":"FMD4H45OD6F45TUL","created_at":"2026-07-05T06:57:13Z"},{"alias_kind":"pith_short_8","alias_value":"FMD4H45O","created_at":"2026-07-05T06:57:13Z"}],"graph_snapshots":[{"event_id":"sha256:9386f2b63ccc492def04f05d0416abfa63ba49765f42186f19bbebf9345c33a6","target":"graph","created_at":"2026-07-05T06:57:13Z","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/2310.02782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of discovering algorithms that can perform well on a wide range of RL tasks. Despite impressive initial results from algorithms such as Learned Policy Gradient (LPG), there remains a generalization gap when these algorithms are applied to unseen environments. In this work, we examine how characteristics of the meta-training distribution impact the generalization perf","authors_text":"Chris Lu, Gregory Farquhar, Jack Parker-Holder, Jakob Nicolaus Foerster, Matthew Thomas Jackson, Minqi Jiang, Risto Vuorio, Shimon Whiteson","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T12:52:56Z","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02782","kind":"arxiv","version":1},"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":"sha256:0e7610aeccd10e626ae746c9499850aa18f79c6316597f02a2921b65244c02ac","target":"record","created_at":"2026-07-05T06:57:13Z","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":"36e6a255b551a38bb191bb1e6366efa5c14adf733011c02a157038835ade2026","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T12:52:56Z","title_canon_sha256":"bf5197ae70bd11b44226f53840c32175c146194a99d964d547ed6840d0d426af"},"schema_version":"1.0","source":{"id":"2310.02782","kind":"arxiv","version":1}},"canonical_sha256":"2b07c3f3ae1f8bcece8ba5674d1a7282f1f81bca4b04fd2da7becc909de88dbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b07c3f3ae1f8bcece8ba5674d1a7282f1f81bca4b04fd2da7becc909de88dbb","first_computed_at":"2026-07-05T06:57:13.876680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:13.876680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5BTtsXwdiyrQDFGUq+LOfpK71WEJ+oPqzxpyOQlQu66SKvEiRqQ0TAHhkzoE5bzTgEYmkrJq1FUoeeQhdgrCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:13.877221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e7610aeccd10e626ae746c9499850aa18f79c6316597f02a2921b65244c02ac","sha256:9386f2b63ccc492def04f05d0416abfa63ba49765f42186f19bbebf9345c33a6"],"state_sha256":"72aa22932982b75a7b24637990eb275a8855abdb8f08b3a307b8e7c49c0662e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4O+n9rcJoBkGFpkkqrPGoO0MUSeIOKfiamKntPMIQ4fbBdQKWwdXx2+HJLOCG1I04JkmMk9yZRN4j6fWbJIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:15:52.219278Z","bundle_sha256":"e7a8ef98e5d95626c546a7bc8b895a2f5b59dca5a0c56982f6d349c9adf13ed5"}}