{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:P4APBI2ZDBPF4WKSGMXQG3Z4UU","short_pith_number":"pith:P4APBI2Z","schema_version":"1.0","canonical_sha256":"7f00f0a359185e5e5952332f036f3ca53b46a5dff02c85b6b87851d340ad40ac","source":{"kind":"arxiv","id":"1909.00025","version":2},"attestation_state":"computed","paper":{"title":"Meta-Learning with Warped Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrei A. Rusu, Francesco Visin, Hujun Yin, Raia Hadsell, Razvan Pascanu, Sebastian Flennerhag","submitted_at":"2019-08-30T18:27:35Z","abstract_excerpt":"Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a neural network that directly produces updates or by attempting to learn better initialisations or scaling factors for a gradient-based update rule. Both of these approaches pose challenges. On one hand, directly producing an update forgoes a useful inductive bias and can easily lead to non-converging behaviour. On the other hand, approaches that try to contr"},"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":"1909.00025","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-30T18:27:35Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"4d306cd8542a98814b406f7e512ed2a850ea16a324f2e7ca72192bf383c0f7d5","abstract_canon_sha256":"59dccbf85bcac1fe801a2cd0626f9aeae7d58b7ac26cadf53ca0ab355415ee97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:36.537013Z","signature_b64":"Q/dh5vOaC/PH7AiFmpb5uyF+FMUCNmAjF4u8v0VbvFm2smGVLn0mowRcpdPptLAguAY4/EyU0ZiiBPbe4fmMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f00f0a359185e5e5952332f036f3ca53b46a5dff02c85b6b87851d340ad40ac","last_reissued_at":"2026-07-05T00:41:36.536575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:36.536575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning with Warped Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrei A. Rusu, Francesco Visin, Hujun Yin, Raia Hadsell, Razvan Pascanu, Sebastian Flennerhag","submitted_at":"2019-08-30T18:27:35Z","abstract_excerpt":"Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a neural network that directly produces updates or by attempting to learn better initialisations or scaling factors for a gradient-based update rule. Both of these approaches pose challenges. On one hand, directly producing an update forgoes a useful inductive bias and can easily lead to non-converging behaviour. On the other hand, approaches that try to contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00025","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/1909.00025/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":"1909.00025","created_at":"2026-07-05T00:41:36.536633+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00025v2","created_at":"2026-07-05T00:41:36.536633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00025","created_at":"2026-07-05T00:41:36.536633+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4APBI2ZDBPF","created_at":"2026-07-05T00:41:36.536633+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4APBI2ZDBPF4WKS","created_at":"2026-07-05T00:41:36.536633+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4APBI2Z","created_at":"2026-07-05T00:41:36.536633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15963","citing_title":"Evaluating Data Influence in Meta Learning","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU","json":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU.json","graph_json":"https://pith.science/api/pith-number/P4APBI2ZDBPF4WKSGMXQG3Z4UU/graph.json","events_json":"https://pith.science/api/pith-number/P4APBI2ZDBPF4WKSGMXQG3Z4UU/events.json","paper":"https://pith.science/paper/P4APBI2Z"},"agent_actions":{"view_html":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU","download_json":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU.json","view_paper":"https://pith.science/paper/P4APBI2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00025&json=true","fetch_graph":"https://pith.science/api/pith-number/P4APBI2ZDBPF4WKSGMXQG3Z4UU/graph.json","fetch_events":"https://pith.science/api/pith-number/P4APBI2ZDBPF4WKSGMXQG3Z4UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU/action/storage_attestation","attest_author":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU/action/author_attestation","sign_citation":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU/action/citation_signature","submit_replication":"https://pith.science/pith/P4APBI2ZDBPF4WKSGMXQG3Z4UU/action/replication_record"}},"created_at":"2026-07-05T00:41:36.536633+00:00","updated_at":"2026-07-05T00:41:36.536633+00:00"}