{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DZSMDMJML4SPYKKWBKSASOQC36","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":"24fe5ed33647d9927e2406ca0fcb833479e8385c492ce270f984e890da71ce75","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T16:31:38Z","title_canon_sha256":"5268c262f1e77f05892fae3b3e0bf0c3953e5c22f3751cc5fa8c1e9cf76557ef"},"schema_version":"1.0","source":{"id":"2507.17668","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17668","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17668v2","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17668","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"pith_short_12","alias_value":"DZSMDMJML4SP","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"pith_short_16","alias_value":"DZSMDMJML4SPYKKW","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"pith_short_8","alias_value":"DZSMDMJM","created_at":"2026-07-05T12:08:05Z"}],"graph_snapshots":[{"event_id":"sha256:c39c6a7abe72bd5f7ba542eeb7be7ab74431c515299eab5364d5e854594eaef2","target":"graph","created_at":"2026-07-05T12:08:05Z","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/2507.17668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The process of meta-learning algorithms from data, instead of relying on manual design, is growing in popularity as a paradigm for improving the performance of machine learning systems. Meta-learning shows particular promise for reinforcement learning (RL), where algorithms are often adapted from supervised or unsupervised learning despite their suboptimality for RL. However, until now there has been a severe lack of comparison between different meta-learning algorithms, such as using evolution to optimise over black-box functions or LLMs to propose code. In this paper, we carry out this empir","authors_text":"Alexander David Goldie, Jakob Nicolaus Foerster, Jaron Cohen, Shimon Whiteson, Zilin Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T16:31:38Z","title":"How Should We Meta-Learn Reinforcement Learning Algorithms?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17668","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":"sha256:220dd04fec6c668c50731543c3ae1a1d94e7910a6aa41cfd33a5569886cdc1c2","target":"record","created_at":"2026-07-05T12:08:05Z","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":"24fe5ed33647d9927e2406ca0fcb833479e8385c492ce270f984e890da71ce75","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T16:31:38Z","title_canon_sha256":"5268c262f1e77f05892fae3b3e0bf0c3953e5c22f3751cc5fa8c1e9cf76557ef"},"schema_version":"1.0","source":{"id":"2507.17668","kind":"arxiv","version":2}},"canonical_sha256":"1e64c1b12c5f24fc29560aa4093a02dfb35380767504bc4c54a1d8fada762590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e64c1b12c5f24fc29560aa4093a02dfb35380767504bc4c54a1d8fada762590","first_computed_at":"2026-07-05T12:08:05.564573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:05.564573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qI1/WOcoToV54W43SjsCD2ru6IJ47Wynod1WxdDctrMxjUu0DLjwufKlRZbJUaT6k+luMkM5tXF3bRl9qBmMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:05.565275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17668","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:220dd04fec6c668c50731543c3ae1a1d94e7910a6aa41cfd33a5569886cdc1c2","sha256:c39c6a7abe72bd5f7ba542eeb7be7ab74431c515299eab5364d5e854594eaef2"],"state_sha256":"19f722cb2cd2c37d4b81204acdb072f1d0e4f55b10209493424748ef295825bb"}