{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Q24BGQHR4DL7O5PDVNMVANN5ME","short_pith_number":"pith:Q24BGQHR","schema_version":"1.0","canonical_sha256":"86b81340f1e0d7f775e3ab595035bd610dd1a525f29233af8e60bf62bbe9923e","source":{"kind":"arxiv","id":"1710.11622","version":3},"attestation_state":"computed","paper":{"title":"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Sergey Levine","submitted_at":"2017-10-31T17:55:42Z","abstract_excerpt":"Learning to learn is a powerful paradigm for enabling models to learn from data more effectively and efficiently. A popular approach to meta-learning is to train a recurrent model to read in a training dataset as input and output the parameters of a learned model, or output predictions for new test inputs. Alternatively, a more recent approach to meta-learning aims to acquire deep representations that can be effectively fine-tuned, via standard gradient descent, to new tasks. In this paper, we consider the meta-learning problem from the perspective of universality, formalizing the notion of le"},"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":"1710.11622","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T17:55:42Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"d8ef67b787472833901a08ddf89e43a597c6b65f024ff036ff586b5834676dd1","abstract_canon_sha256":"1d6a7c6467d1fffbbc0e4d329397812de5c44eef46ecb6e486f8b2fff1905a76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:16.490606Z","signature_b64":"Q9EQHihS9kZixLZdUofunG6E3wyH1A8EKbZKYgfVSheOXwy8bbYh+I0HDTb82WmLhrTuhiIVrTz3LkyVbh+DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b81340f1e0d7f775e3ab595035bd610dd1a525f29233af8e60bf62bbe9923e","last_reissued_at":"2026-05-18T00:23:16.490001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:16.490001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Sergey Levine","submitted_at":"2017-10-31T17:55:42Z","abstract_excerpt":"Learning to learn is a powerful paradigm for enabling models to learn from data more effectively and efficiently. A popular approach to meta-learning is to train a recurrent model to read in a training dataset as input and output the parameters of a learned model, or output predictions for new test inputs. Alternatively, a more recent approach to meta-learning aims to acquire deep representations that can be effectively fine-tuned, via standard gradient descent, to new tasks. In this paper, we consider the meta-learning problem from the perspective of universality, formalizing the notion of le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11622","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.11622","created_at":"2026-05-18T00:23:16.490123+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.11622v3","created_at":"2026-05-18T00:23:16.490123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11622","created_at":"2026-05-18T00:23:16.490123+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q24BGQHR4DL7","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q24BGQHR4DL7O5PD","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q24BGQHR","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02300","citing_title":"A Meta Reinforcement Learning Approach to Goals-Based Wealth Management","ref_index":86,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME","json":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME.json","graph_json":"https://pith.science/api/pith-number/Q24BGQHR4DL7O5PDVNMVANN5ME/graph.json","events_json":"https://pith.science/api/pith-number/Q24BGQHR4DL7O5PDVNMVANN5ME/events.json","paper":"https://pith.science/paper/Q24BGQHR"},"agent_actions":{"view_html":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME","download_json":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME.json","view_paper":"https://pith.science/paper/Q24BGQHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.11622&json=true","fetch_graph":"https://pith.science/api/pith-number/Q24BGQHR4DL7O5PDVNMVANN5ME/graph.json","fetch_events":"https://pith.science/api/pith-number/Q24BGQHR4DL7O5PDVNMVANN5ME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME/action/storage_attestation","attest_author":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME/action/author_attestation","sign_citation":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME/action/citation_signature","submit_replication":"https://pith.science/pith/Q24BGQHR4DL7O5PDVNMVANN5ME/action/replication_record"}},"created_at":"2026-05-18T00:23:16.490123+00:00","updated_at":"2026-05-18T00:23:16.490123+00:00"}