{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:545D5DF3HATVFVKKJWSUQ37XTP","short_pith_number":"pith:545D5DF3","schema_version":"1.0","canonical_sha256":"ef3a3e8cbb382752d54a4da5486ff79beea9cb86b6906990fd898d28b18d4d34","source":{"kind":"arxiv","id":"1812.06080","version":3},"attestation_state":"computed","paper":{"title":"Reconciling meta-learning and continual learning with online mixtures of tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Erin Grant, Ghassen Jerfel, Katherine Heller, Thomas L. Griffiths","submitted_at":"2018-12-14T18:59:03Z","abstract_excerpt":"Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably dissimilar or change over time. We use the connection between gradient-based meta-learning and hierarchical Bayes to propose a Dirichlet process mixture of hierarchical Bayesian models over the parameters of an arbitrary parametric model such as a neural network. In contrast to consolidating inductive biases into a single set of hyperparameters, our approac"},"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":"1812.06080","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T18:59:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a7cf2568057fdb6408a9358fdb09f02d79cb599a64b2bf34058fddfac13a398","abstract_canon_sha256":"e9a9e120dfc92f42d20a5b72c610d514aeca3e36e39bfeb1a26336dfc1bd0fa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:58.561378Z","signature_b64":"pDxtLX1Z9Wo0hfpUoT6mWAqKxl1ljweh5SqjC8s0maRCMZYKBRzbX8ic9mWLRFUK7vxtA14vxCSKEMTro4gQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3a3e8cbb382752d54a4da5486ff79beea9cb86b6906990fd898d28b18d4d34","last_reissued_at":"2026-05-17T23:42:58.560925Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:58.560925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconciling meta-learning and continual learning with online mixtures of tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Erin Grant, Ghassen Jerfel, Katherine Heller, Thomas L. Griffiths","submitted_at":"2018-12-14T18:59:03Z","abstract_excerpt":"Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably dissimilar or change over time. We use the connection between gradient-based meta-learning and hierarchical Bayes to propose a Dirichlet process mixture of hierarchical Bayesian models over the parameters of an arbitrary parametric model such as a neural network. In contrast to consolidating inductive biases into a single set of hyperparameters, our approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06080","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":"1812.06080","created_at":"2026-05-17T23:42:58.560991+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.06080v3","created_at":"2026-05-17T23:42:58.560991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06080","created_at":"2026-05-17T23:42:58.560991+00:00"},{"alias_kind":"pith_short_12","alias_value":"545D5DF3HATV","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"545D5DF3HATVFVKK","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"545D5DF3","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP","json":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP.json","graph_json":"https://pith.science/api/pith-number/545D5DF3HATVFVKKJWSUQ37XTP/graph.json","events_json":"https://pith.science/api/pith-number/545D5DF3HATVFVKKJWSUQ37XTP/events.json","paper":"https://pith.science/paper/545D5DF3"},"agent_actions":{"view_html":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP","download_json":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP.json","view_paper":"https://pith.science/paper/545D5DF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.06080&json=true","fetch_graph":"https://pith.science/api/pith-number/545D5DF3HATVFVKKJWSUQ37XTP/graph.json","fetch_events":"https://pith.science/api/pith-number/545D5DF3HATVFVKKJWSUQ37XTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP/action/storage_attestation","attest_author":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP/action/author_attestation","sign_citation":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP/action/citation_signature","submit_replication":"https://pith.science/pith/545D5DF3HATVFVKKJWSUQ37XTP/action/replication_record"}},"created_at":"2026-05-17T23:42:58.560991+00:00","updated_at":"2026-05-17T23:42:58.560991+00:00"}