{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Y75BWMHG2W6TN7CVJ7S7NEC53K","short_pith_number":"pith:Y75BWMHG","schema_version":"1.0","canonical_sha256":"c7fa1b30e6d5bd36fc554fe5f6905dda8f0076316f381bc3898ba2b61208a476","source":{"kind":"arxiv","id":"1909.09157","version":2},"attestation_state":"computed","paper":{"title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aniruddh Raghu, Maithra Raghu, Oriol Vinyals, Samy Bengio","submitted_at":"2019-09-19T16:30:42Z","abstract_excerpt":"An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been Model Agnostic Meta-Learning (MAML), a method that consists of two optimization loops, with the outer loop finding a meta-initialization, from which the inner loop can efficiently learn new tasks. Despite MAML's popularity, a fundamental open question remains -- is the effectiveness of MAML due to the meta-initialization being primed for rapid learning (large, efficient changes in the representations) or due to feat"},"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":"1909.09157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-19T16:30:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ee4f26497e00bb87ee991777dc2563ea1d65571816d0aea0fb0b20557e595092","abstract_canon_sha256":"cbb6d03444e142d492bf349ceba884029d503e10bbafb6a77c2e8479ebef2e4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:14.683762Z","signature_b64":"2xJxE87yf0wLmxO/ccXrVK09PUWB32ySJFhFc+Lp9mhiHdeMRr+1l3YA5lwWf2JeWoHydf7JRtcSflwj21N2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7fa1b30e6d5bd36fc554fe5f6905dda8f0076316f381bc3898ba2b61208a476","last_reissued_at":"2026-07-05T00:40:14.683214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:14.683214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aniruddh Raghu, Maithra Raghu, Oriol Vinyals, Samy Bengio","submitted_at":"2019-09-19T16:30:42Z","abstract_excerpt":"An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been Model Agnostic Meta-Learning (MAML), a method that consists of two optimization loops, with the outer loop finding a meta-initialization, from which the inner loop can efficiently learn new tasks. Despite MAML's popularity, a fundamental open question remains -- is the effectiveness of MAML due to the meta-initialization being primed for rapid learning (large, efficient changes in the representations) or due to feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09157","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/1909.09157/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":"1909.09157","created_at":"2026-07-05T00:40:14.683272+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.09157v2","created_at":"2026-07-05T00:40:14.683272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09157","created_at":"2026-07-05T00:40:14.683272+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y75BWMHG2W6T","created_at":"2026-07-05T00:40:14.683272+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y75BWMHG2W6TN7CV","created_at":"2026-07-05T00:40:14.683272+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y75BWMHG","created_at":"2026-07-05T00:40:14.683272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.24985","citing_title":"Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17902","citing_title":"DUPLE: An Intelligent Cross-Deployment Recognition Framework for Fiber-Optic Perimeter Security under Scarce Target Labels","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14632","citing_title":"Continual Few-shot Adaptation for Synthetic Fingerprint Detection","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24985","citing_title":"Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13672","citing_title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25275","citing_title":"Graph-Conditioned Meta-Optimizer for QAOA Parameter Generation on Multiple Problem Classes","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06431","citing_title":"Second-Order Bilevel Optimization with Accelerated Convergence Rates","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13263","citing_title":"Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K","json":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K.json","graph_json":"https://pith.science/api/pith-number/Y75BWMHG2W6TN7CVJ7S7NEC53K/graph.json","events_json":"https://pith.science/api/pith-number/Y75BWMHG2W6TN7CVJ7S7NEC53K/events.json","paper":"https://pith.science/paper/Y75BWMHG"},"agent_actions":{"view_html":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K","download_json":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K.json","view_paper":"https://pith.science/paper/Y75BWMHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.09157&json=true","fetch_graph":"https://pith.science/api/pith-number/Y75BWMHG2W6TN7CVJ7S7NEC53K/graph.json","fetch_events":"https://pith.science/api/pith-number/Y75BWMHG2W6TN7CVJ7S7NEC53K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K/action/storage_attestation","attest_author":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K/action/author_attestation","sign_citation":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K/action/citation_signature","submit_replication":"https://pith.science/pith/Y75BWMHG2W6TN7CVJ7S7NEC53K/action/replication_record"}},"created_at":"2026-07-05T00:40:14.683272+00:00","updated_at":"2026-07-05T00:40:14.683272+00:00"}