{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:57VXPP5OA3TVLGIW7MHD36W7QZ","short_pith_number":"pith:57VXPP5O","schema_version":"1.0","canonical_sha256":"efeb77bfae06e7559916fb0e3dfadf864df7d762d2359be7b361e4aab0e9e396","source":{"kind":"arxiv","id":"2207.09405","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Generational Population-Based Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Cong Lu, Jack Parker-Holder, Michael A. Osborne, Philip J. Ball, Vu Nguyen, Xingchen Wan","submitted_at":"2022-07-19T16:57:38Z","abstract_excerpt":"Reinforcement learning (RL) offers the potential for training generally capable agents that can interact autonomously in the real world. However, one key limitation is the brittleness of RL algorithms to core hyperparameters and network architecture choice. Furthermore, non-stationarities such as evolving training data and increased agent complexity mean that different hyperparameters and architectures may be optimal at different points of training. This motivates AutoRL, a class of methods seeking to automate these design choices. One prominent class of AutoRL methods is Population-Based Trai"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-19T16:57:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3bacb100bd28754816d7cc76ef818899658492c9a5e202be520e1b8d84c984ef","abstract_canon_sha256":"0357abd18d76a520579a723489fcd98fa371cc1e48d43be82ecd9f0f86220fee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:49.441969Z","signature_b64":"lU+wZkD77uJLvmziLwfvkaCmoI4JXr+YKLNbzedCxWW+eYQc8YCOFcLrRddJkTGCM6f0ujO5hg2PT5h9mGDMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efeb77bfae06e7559916fb0e3dfadf864df7d762d2359be7b361e4aab0e9e396","last_reissued_at":"2026-07-05T04:41:49.441633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:49.441633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Generational Population-Based Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Cong Lu, Jack Parker-Holder, Michael A. Osborne, Philip J. Ball, Vu Nguyen, Xingchen Wan","submitted_at":"2022-07-19T16:57:38Z","abstract_excerpt":"Reinforcement learning (RL) offers the potential for training generally capable agents that can interact autonomously in the real world. However, one key limitation is the brittleness of RL algorithms to core hyperparameters and network architecture choice. Furthermore, non-stationarities such as evolving training data and increased agent complexity mean that different hyperparameters and architectures may be optimal at different points of training. This motivates AutoRL, a class of methods seeking to automate these design choices. One prominent class of AutoRL methods is Population-Based Trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09405","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/2207.09405/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.09405","created_at":"2026-07-05T04:41:49.441688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09405v1","created_at":"2026-07-05T04:41:49.441688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09405","created_at":"2026-07-05T04:41:49.441688+00:00"},{"alias_kind":"pith_short_12","alias_value":"57VXPP5OA3TV","created_at":"2026-07-05T04:41:49.441688+00:00"},{"alias_kind":"pith_short_16","alias_value":"57VXPP5OA3TVLGIW","created_at":"2026-07-05T04:41:49.441688+00:00"},{"alias_kind":"pith_short_8","alias_value":"57VXPP5O","created_at":"2026-07-05T04:41:49.441688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ","json":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ.json","graph_json":"https://pith.science/api/pith-number/57VXPP5OA3TVLGIW7MHD36W7QZ/graph.json","events_json":"https://pith.science/api/pith-number/57VXPP5OA3TVLGIW7MHD36W7QZ/events.json","paper":"https://pith.science/paper/57VXPP5O"},"agent_actions":{"view_html":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ","download_json":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ.json","view_paper":"https://pith.science/paper/57VXPP5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09405&json=true","fetch_graph":"https://pith.science/api/pith-number/57VXPP5OA3TVLGIW7MHD36W7QZ/graph.json","fetch_events":"https://pith.science/api/pith-number/57VXPP5OA3TVLGIW7MHD36W7QZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ/action/storage_attestation","attest_author":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ/action/author_attestation","sign_citation":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ/action/citation_signature","submit_replication":"https://pith.science/pith/57VXPP5OA3TVLGIW7MHD36W7QZ/action/replication_record"}},"created_at":"2026-07-05T04:41:49.441688+00:00","updated_at":"2026-07-05T04:41:49.441688+00:00"}