{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y542OGQWR2JR53QZPM4QWAKOY2","short_pith_number":"pith:Y542OGQW","schema_version":"1.0","canonical_sha256":"c779a71a168e931eee197b390b014ec6986e1593ceb09a76cd72e2013f4ce6ed","source":{"kind":"arxiv","id":"2212.04180","version":1},"attestation_state":"computed","paper":{"title":"evosax: JAX-based Evolution Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Robert Tjarko Lange","submitted_at":"2022-12-08T10:34:42Z","abstract_excerpt":"The deep learning revolution has greatly been accelerated by the 'hardware lottery': Recent advances in modern hardware accelerators and compilers paved the way for large-scale batch gradient optimization. Evolutionary optimization, on the other hand, has mainly relied on CPU-parallelism, e.g. using Dask scheduling and distributed multi-host infrastructure. Here we argue that also modern evolutionary computation can significantly benefit from the massive computational throughput provided by GPUs and TPUs. In order to better harness these resources and to enable the next generation of black-box"},"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":"2212.04180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-12-08T10:34:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce1e5ef1c6eeb9f152b1f514e555bc3ff9c09a2b5703679a8c14f5be077ac36d","abstract_canon_sha256":"05f008f636d741a72078eec713ccedb973e863c3b76159cac045a5946d0531ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:37.373979Z","signature_b64":"nfEFe7d9DUaFvNmrXyu9cRiitZcPEGniWv+3F2ifwKBHDQV5MeDHxucvqzZaptUyP3/jjyTaevgL3lCnxtmvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c779a71a168e931eee197b390b014ec6986e1593ceb09a76cd72e2013f4ce6ed","last_reissued_at":"2026-07-05T05:23:37.373586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:37.373586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"evosax: JAX-based Evolution Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Robert Tjarko Lange","submitted_at":"2022-12-08T10:34:42Z","abstract_excerpt":"The deep learning revolution has greatly been accelerated by the 'hardware lottery': Recent advances in modern hardware accelerators and compilers paved the way for large-scale batch gradient optimization. Evolutionary optimization, on the other hand, has mainly relied on CPU-parallelism, e.g. using Dask scheduling and distributed multi-host infrastructure. Here we argue that also modern evolutionary computation can significantly benefit from the massive computational throughput provided by GPUs and TPUs. In order to better harness these resources and to enable the next generation of black-box"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04180","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/2212.04180/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":"2212.04180","created_at":"2026-07-05T05:23:37.373642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04180v1","created_at":"2026-07-05T05:23:37.373642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04180","created_at":"2026-07-05T05:23:37.373642+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y542OGQWR2JR","created_at":"2026-07-05T05:23:37.373642+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y542OGQWR2JR53QZ","created_at":"2026-07-05T05:23:37.373642+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y542OGQW","created_at":"2026-07-05T05:23:37.373642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25761","citing_title":"Bridging Spherical Black-Box Optimizers","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2","json":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2.json","graph_json":"https://pith.science/api/pith-number/Y542OGQWR2JR53QZPM4QWAKOY2/graph.json","events_json":"https://pith.science/api/pith-number/Y542OGQWR2JR53QZPM4QWAKOY2/events.json","paper":"https://pith.science/paper/Y542OGQW"},"agent_actions":{"view_html":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2","download_json":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2.json","view_paper":"https://pith.science/paper/Y542OGQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04180&json=true","fetch_graph":"https://pith.science/api/pith-number/Y542OGQWR2JR53QZPM4QWAKOY2/graph.json","fetch_events":"https://pith.science/api/pith-number/Y542OGQWR2JR53QZPM4QWAKOY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2/action/storage_attestation","attest_author":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2/action/author_attestation","sign_citation":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2/action/citation_signature","submit_replication":"https://pith.science/pith/Y542OGQWR2JR53QZPM4QWAKOY2/action/replication_record"}},"created_at":"2026-07-05T05:23:37.373642+00:00","updated_at":"2026-07-05T05:23:37.373642+00:00"}