{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NV4POQZP733TPDP7HNT2SJHO76","short_pith_number":"pith:NV4POQZP","schema_version":"1.0","canonical_sha256":"6d78f7432ffef7378dff3b67a924eeffb678254e7b68b100b32bab2779d9c25c","source":{"kind":"arxiv","id":"2103.06435","version":1},"attestation_state":"computed","paper":{"title":"Population-Based Evolution Optimizes a Meta-Learning Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Kevin Frans, Olaf Witkowski","submitted_at":"2021-03-11T03:45:43Z","abstract_excerpt":"Meta-learning models, or models that learn to learn, have been a long-desired target for their ability to quickly solve new tasks. Traditional meta-learning methods can require expensive inner and outer loops, thus there is demand for algorithms that discover strong learners without explicitly searching for them. We draw parallels to the study of evolvable genomes in evolutionary systems -- genomes with a strong capacity to adapt -- and propose that meta-learning and adaptive evolvability optimize for the same objective: high performance after a set of learning iterations. We argue that popula"},"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":"2103.06435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-03-11T03:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"9a698ba0ad27740a8510be3adc50e2eb87e30c3127617dc2d3b25f4f885c564f","abstract_canon_sha256":"8ebfbec7fc16c9c55c9e7e1b647ee1a26fa73043c1ab1f9066f6aceaf1bf61a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:09.109337Z","signature_b64":"/Rvp6Ij75RunUwjCk5yNQvl5xRuEgYk1PnDViUz1f292SLtherUL80XFxY/WbmwOLgpFdHoiWndjhCoKpT2vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d78f7432ffef7378dff3b67a924eeffb678254e7b68b100b32bab2779d9c25c","last_reissued_at":"2026-07-05T02:22:09.108881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:09.108881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Population-Based Evolution Optimizes a Meta-Learning Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Kevin Frans, Olaf Witkowski","submitted_at":"2021-03-11T03:45:43Z","abstract_excerpt":"Meta-learning models, or models that learn to learn, have been a long-desired target for their ability to quickly solve new tasks. Traditional meta-learning methods can require expensive inner and outer loops, thus there is demand for algorithms that discover strong learners without explicitly searching for them. We draw parallels to the study of evolvable genomes in evolutionary systems -- genomes with a strong capacity to adapt -- and propose that meta-learning and adaptive evolvability optimize for the same objective: high performance after a set of learning iterations. We argue that popula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06435","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/2103.06435/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":"2103.06435","created_at":"2026-07-05T02:22:09.108937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06435v1","created_at":"2026-07-05T02:22:09.108937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06435","created_at":"2026-07-05T02:22:09.108937+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV4POQZP733T","created_at":"2026-07-05T02:22:09.108937+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV4POQZP733TPDP7","created_at":"2026-07-05T02:22:09.108937+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV4POQZP","created_at":"2026-07-05T02:22:09.108937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76","json":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76.json","graph_json":"https://pith.science/api/pith-number/NV4POQZP733TPDP7HNT2SJHO76/graph.json","events_json":"https://pith.science/api/pith-number/NV4POQZP733TPDP7HNT2SJHO76/events.json","paper":"https://pith.science/paper/NV4POQZP"},"agent_actions":{"view_html":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76","download_json":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76.json","view_paper":"https://pith.science/paper/NV4POQZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06435&json=true","fetch_graph":"https://pith.science/api/pith-number/NV4POQZP733TPDP7HNT2SJHO76/graph.json","fetch_events":"https://pith.science/api/pith-number/NV4POQZP733TPDP7HNT2SJHO76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76/action/storage_attestation","attest_author":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76/action/author_attestation","sign_citation":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76/action/citation_signature","submit_replication":"https://pith.science/pith/NV4POQZP733TPDP7HNT2SJHO76/action/replication_record"}},"created_at":"2026-07-05T02:22:09.108937+00:00","updated_at":"2026-07-05T02:22:09.108937+00:00"}