{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6UGQ4363L6ARBKHOQ4LE3SRQYP","short_pith_number":"pith:6UGQ4363","schema_version":"1.0","canonical_sha256":"f50d0e6fdb5f8110a8ee87164dca30c3f33fbff086f15dade855bf998ad010c4","source":{"kind":"arxiv","id":"1903.03096","version":4},"attestation_state":"computed","paper":{"title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carles Gelada, Eleni Triantafillou, Hugo Larochelle, Kelvin Xu, Kevin Swersky, Pascal Lamblin, Pierre-Antoine Manzagol, Ross Goroshin, Tyler Zhu, Utku Evci, Vincent Dumoulin","submitted_at":"2019-03-07T18:48:55Z","abstract_excerpt":"Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To address this limitation, we propose Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks. We experiment with popular baselines and meta-learners on Meta-Dataset, along with a competitive method that we propose. We analyze performance as a function of various chara"},"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":"1903.03096","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T18:48:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f37e6961fa0a91a0531f8a4eaf60d767f3a708d7253a1ed115526d05aedaa63","abstract_canon_sha256":"76e74a30b2d63424d133a306c6b1624f784cad417b4a6ded4b59db3977ebe74c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:50.135864Z","signature_b64":"4MxE97yU4tkVGi2rr/wFUP0yh1ZwwCFONslXwIkiv5DJZCuVgn73TOaBRlyD1rZts1M9Wxu6bb1hsbJsaPqNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f50d0e6fdb5f8110a8ee87164dca30c3f33fbff086f15dade855bf998ad010c4","last_reissued_at":"2026-07-05T00:53:50.135454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:50.135454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carles Gelada, Eleni Triantafillou, Hugo Larochelle, Kelvin Xu, Kevin Swersky, Pascal Lamblin, Pierre-Antoine Manzagol, Ross Goroshin, Tyler Zhu, Utku Evci, Vincent Dumoulin","submitted_at":"2019-03-07T18:48:55Z","abstract_excerpt":"Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To address this limitation, we propose Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks. We experiment with popular baselines and meta-learners on Meta-Dataset, along with a competitive method that we propose. We analyze performance as a function of various chara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03096","kind":"arxiv","version":4},"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/1903.03096/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":"1903.03096","created_at":"2026-07-05T00:53:50.135513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03096v4","created_at":"2026-07-05T00:53:50.135513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03096","created_at":"2026-07-05T00:53:50.135513+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UGQ4363L6AR","created_at":"2026-07-05T00:53:50.135513+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UGQ4363L6ARBKHO","created_at":"2026-07-05T00:53:50.135513+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UGQ4363","created_at":"2026-07-05T00:53:50.135513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1910.04867","citing_title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","ref_index":15,"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":171,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17569","citing_title":"MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP","json":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP.json","graph_json":"https://pith.science/api/pith-number/6UGQ4363L6ARBKHOQ4LE3SRQYP/graph.json","events_json":"https://pith.science/api/pith-number/6UGQ4363L6ARBKHOQ4LE3SRQYP/events.json","paper":"https://pith.science/paper/6UGQ4363"},"agent_actions":{"view_html":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP","download_json":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP.json","view_paper":"https://pith.science/paper/6UGQ4363","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03096&json=true","fetch_graph":"https://pith.science/api/pith-number/6UGQ4363L6ARBKHOQ4LE3SRQYP/graph.json","fetch_events":"https://pith.science/api/pith-number/6UGQ4363L6ARBKHOQ4LE3SRQYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP/action/storage_attestation","attest_author":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP/action/author_attestation","sign_citation":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP/action/citation_signature","submit_replication":"https://pith.science/pith/6UGQ4363L6ARBKHOQ4LE3SRQYP/action/replication_record"}},"created_at":"2026-07-05T00:53:50.135513+00:00","updated_at":"2026-07-05T00:53:50.135513+00:00"}