{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SOLO2ZGHLHM3PDRCLUXE7DRVIE","short_pith_number":"pith:SOLO2ZGH","schema_version":"1.0","canonical_sha256":"9396ed64c759d9b78e225d2e4f8e354107e808128a8fc3f51378ed8bb5ee653c","source":{"kind":"arxiv","id":"1910.01727","version":2},"attestation_state":"computed","paper":{"title":"Generalized Inner Loop Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Artem Molchanov, Brandon Amos, Denis Yarats, Douwe Kiela, Edward Grefenstette, Franziska Meier, Kyunghyun Cho, Phu Mon Htut, Soumith Chintala","submitted_at":"2019-10-03T21:41:56Z","abstract_excerpt":"Many (but not all) approaches self-qualifying as \"meta-learning\" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a formalization of this shared pattern, which we call GIMLI, prove its general requirements, and derive a general-purpose algorithm for implementing similar approaches. Based on this analysis and algorithm, we describe a library of our design, higher, which we share with the community to assist and enable future research into these kinds of meta-learning approaches. We end the pap"},"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":"1910.01727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-03T21:41:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2b8f34deb170cd4da3e0c26b8987d5a7f4c5cfc7bea4af36564a1c7ab7dcd659","abstract_canon_sha256":"96e2aeed90537d30dffe9dbb134c605e78d987d924d0477a2c3a46e7ba06f9cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:05.203248Z","signature_b64":"a4QPTrhW1tAgYhX9x+UcrqcaxbkbVVkWlZIrvFAFro6Qf6FcYp0hVYgx4SlE6OJ5Wwdn8a66SLyv8EdvsaOvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9396ed64c759d9b78e225d2e4f8e354107e808128a8fc3f51378ed8bb5ee653c","last_reissued_at":"2026-07-05T00:10:05.202865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:05.202865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Inner Loop Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Artem Molchanov, Brandon Amos, Denis Yarats, Douwe Kiela, Edward Grefenstette, Franziska Meier, Kyunghyun Cho, Phu Mon Htut, Soumith Chintala","submitted_at":"2019-10-03T21:41:56Z","abstract_excerpt":"Many (but not all) approaches self-qualifying as \"meta-learning\" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a formalization of this shared pattern, which we call GIMLI, prove its general requirements, and derive a general-purpose algorithm for implementing similar approaches. Based on this analysis and algorithm, we describe a library of our design, higher, which we share with the community to assist and enable future research into these kinds of meta-learning approaches. We end the pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01727","kind":"arxiv","version":2},"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/1910.01727/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":"1910.01727","created_at":"2026-07-05T00:10:05.202915+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.01727v2","created_at":"2026-07-05T00:10:05.202915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01727","created_at":"2026-07-05T00:10:05.202915+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOLO2ZGHLHM3","created_at":"2026-07-05T00:10:05.202915+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOLO2ZGHLHM3PDRC","created_at":"2026-07-05T00:10:05.202915+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOLO2ZGH","created_at":"2026-07-05T00:10:05.202915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27358","citing_title":"Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01621","citing_title":"Bilevel learning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE","json":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE.json","graph_json":"https://pith.science/api/pith-number/SOLO2ZGHLHM3PDRCLUXE7DRVIE/graph.json","events_json":"https://pith.science/api/pith-number/SOLO2ZGHLHM3PDRCLUXE7DRVIE/events.json","paper":"https://pith.science/paper/SOLO2ZGH"},"agent_actions":{"view_html":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE","download_json":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE.json","view_paper":"https://pith.science/paper/SOLO2ZGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.01727&json=true","fetch_graph":"https://pith.science/api/pith-number/SOLO2ZGHLHM3PDRCLUXE7DRVIE/graph.json","fetch_events":"https://pith.science/api/pith-number/SOLO2ZGHLHM3PDRCLUXE7DRVIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE/action/storage_attestation","attest_author":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE/action/author_attestation","sign_citation":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE/action/citation_signature","submit_replication":"https://pith.science/pith/SOLO2ZGHLHM3PDRCLUXE7DRVIE/action/replication_record"}},"created_at":"2026-07-05T00:10:05.202915+00:00","updated_at":"2026-07-05T00:10:05.202915+00:00"}