{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IA2J6TZJ3QU52NTTJ23HTVJOOP","short_pith_number":"pith:IA2J6TZJ","schema_version":"1.0","canonical_sha256":"40349f4f29dc29dd36734eb679d52e73faf35f46334c9aebc0110225d2c2d386","source":{"kind":"arxiv","id":"2212.14392","version":1},"attestation_state":"computed","paper":{"title":"Eliminating Meta Optimization Through Self-Referential Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Schmidhuber, Louis Kirsch","submitted_at":"2022-12-29T17:53:40Z","abstract_excerpt":"Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose fitness monotonic execution (FME), a sim"},"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":"2212.14392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-29T17:53:40Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"403a17cb98d2b0fd05331a43a86030e8350e63b2769423e12df958b4056a4a5b","abstract_canon_sha256":"a3db886bd5b021c355794861ac1a5a369715966a5c0857532bcfbf7f1d421f2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:09.568175Z","signature_b64":"oyHgDIBop3BBaYHVbH39mDZF9zelhXuodeMa4eO6zVcHPKMq2HgqUsTTM5F3FJV12z/FPsKoeIM/mmK/qBabCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40349f4f29dc29dd36734eb679d52e73faf35f46334c9aebc0110225d2c2d386","last_reissued_at":"2026-07-05T05:29:09.567716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:09.567716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eliminating Meta Optimization Through Self-Referential Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Schmidhuber, Louis Kirsch","submitted_at":"2022-12-29T17:53:40Z","abstract_excerpt":"Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose fitness monotonic execution (FME), a sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14392","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/2212.14392/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":"2212.14392","created_at":"2026-07-05T05:29:09.567807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.14392v1","created_at":"2026-07-05T05:29:09.567807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14392","created_at":"2026-07-05T05:29:09.567807+00:00"},{"alias_kind":"pith_short_12","alias_value":"IA2J6TZJ3QU5","created_at":"2026-07-05T05:29:09.567807+00:00"},{"alias_kind":"pith_short_16","alias_value":"IA2J6TZJ3QU52NTT","created_at":"2026-07-05T05:29:09.567807+00:00"},{"alias_kind":"pith_short_8","alias_value":"IA2J6TZJ","created_at":"2026-07-05T05:29:09.567807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26294","citing_title":"The Red Queen G\\\"odel Machine: Co-Evolving Agents and Their Evaluators","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26294","citing_title":"The Red Queen G\\\"odel Machine: Co-Evolving Agents and Their Evaluators","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13242","citing_title":"On the Creativity of AI Agents","ref_index":116,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP","json":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP.json","graph_json":"https://pith.science/api/pith-number/IA2J6TZJ3QU52NTTJ23HTVJOOP/graph.json","events_json":"https://pith.science/api/pith-number/IA2J6TZJ3QU52NTTJ23HTVJOOP/events.json","paper":"https://pith.science/paper/IA2J6TZJ"},"agent_actions":{"view_html":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP","download_json":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP.json","view_paper":"https://pith.science/paper/IA2J6TZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.14392&json=true","fetch_graph":"https://pith.science/api/pith-number/IA2J6TZJ3QU52NTTJ23HTVJOOP/graph.json","fetch_events":"https://pith.science/api/pith-number/IA2J6TZJ3QU52NTTJ23HTVJOOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP/action/storage_attestation","attest_author":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP/action/author_attestation","sign_citation":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP/action/citation_signature","submit_replication":"https://pith.science/pith/IA2J6TZJ3QU52NTTJ23HTVJOOP/action/replication_record"}},"created_at":"2026-07-05T05:29:09.567807+00:00","updated_at":"2026-07-05T05:29:09.567807+00:00"}