{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WER7SHJO4N7GOBUAQTZEPPWVGY","short_pith_number":"pith:WER7SHJO","schema_version":"1.0","canonical_sha256":"b123f91d2ee37e67068084f247bed5361faaa6e2adf328c72450fcc6fef1b687","source":{"kind":"arxiv","id":"1801.08930","version":1},"attestation_state":"computed","paper":{"title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Erin Grant, Sergey Levine, Thomas Griffiths, Trevor Darrell","submitted_at":"2018-01-26T18:47:02Z","abstract_excerpt":"Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task. Bayesian hierarchical modeling provides a theoretical framework for formalizing meta-learning as inference for a set of parameters that are shared across tasks. Here, we reformulate the model-agnostic meta-learning algorithm (MAML) of Finn et al. (2017) as a method for probabilistic inference in a hierarchical Bayesian model. In contrast to prior methods for meta-learning via hierarchical Bayes, MAML is naturally applicable to complex function approximator"},"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":"1801.08930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-26T18:47:02Z","cross_cats_sorted":[],"title_canon_sha256":"342ed848e223f6821d9b71dd367fc066d64af83347deeef4564ecd13df3cefea","abstract_canon_sha256":"e5f78333fa42070af7ce65c6631775d6cd4b31531d037db1751373c9e439cd09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:02.652994Z","signature_b64":"a09BTe69xsZ4SrTVq76ep3Kg7AxxSAVoCdh+nZFOyMe9d4eYeG3SvJ3pwSRtrStj3nSHCzV4ieEZuKXvd7GaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b123f91d2ee37e67068084f247bed5361faaa6e2adf328c72450fcc6fef1b687","last_reissued_at":"2026-05-18T00:25:02.652557Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:02.652557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Erin Grant, Sergey Levine, Thomas Griffiths, Trevor Darrell","submitted_at":"2018-01-26T18:47:02Z","abstract_excerpt":"Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task. Bayesian hierarchical modeling provides a theoretical framework for formalizing meta-learning as inference for a set of parameters that are shared across tasks. Here, we reformulate the model-agnostic meta-learning algorithm (MAML) of Finn et al. (2017) as a method for probabilistic inference in a hierarchical Bayesian model. In contrast to prior methods for meta-learning via hierarchical Bayes, MAML is naturally applicable to complex function approximator"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.08930","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":""},"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":"1801.08930","created_at":"2026-05-18T00:25:02.652628+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.08930v1","created_at":"2026-05-18T00:25:02.652628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.08930","created_at":"2026-05-18T00:25:02.652628+00:00"},{"alias_kind":"pith_short_12","alias_value":"WER7SHJO4N7G","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WER7SHJO4N7GOBUA","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WER7SHJO","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12412","citing_title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05115","citing_title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","ref_index":234,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY","json":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY.json","graph_json":"https://pith.science/api/pith-number/WER7SHJO4N7GOBUAQTZEPPWVGY/graph.json","events_json":"https://pith.science/api/pith-number/WER7SHJO4N7GOBUAQTZEPPWVGY/events.json","paper":"https://pith.science/paper/WER7SHJO"},"agent_actions":{"view_html":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY","download_json":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY.json","view_paper":"https://pith.science/paper/WER7SHJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.08930&json=true","fetch_graph":"https://pith.science/api/pith-number/WER7SHJO4N7GOBUAQTZEPPWVGY/graph.json","fetch_events":"https://pith.science/api/pith-number/WER7SHJO4N7GOBUAQTZEPPWVGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY/action/storage_attestation","attest_author":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY/action/author_attestation","sign_citation":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY/action/citation_signature","submit_replication":"https://pith.science/pith/WER7SHJO4N7GOBUAQTZEPPWVGY/action/replication_record"}},"created_at":"2026-05-18T00:25:02.652628+00:00","updated_at":"2026-05-18T00:25:02.652628+00:00"}