{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JBF3RUDCNHB3GWURRBAG2DXQ7A","short_pith_number":"pith:JBF3RUDC","schema_version":"1.0","canonical_sha256":"484bb8d06269c3b35a9188406d0ef0f81f2f3c27923edc4ed8add6e12b8961f8","source":{"kind":"arxiv","id":"2003.04390","version":4},"attestation_state":"computed","paper":{"title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Trevor Darrell, Xiaolong Wang, Yinbo Chen, Zhuang Liu","submitted_at":"2020-03-09T20:06:36Z","abstract_excerpt":"Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective consistent with the testing objective. However, some recent works report that by training for whole-classification, i.e. classification on the whole label-set, it can get comparable or even better embedding than many meta-learning algorithms. The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot le"},"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":"2003.04390","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-09T20:06:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0371ef6907c56baa23233274b43afce4901a9aa5c104cab1ed698e3bb09481ce","abstract_canon_sha256":"feb712562b0553728db0e9e6ca6390f200e86e4b44ee2a6b1bf7ffc3112d5c33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:02.743103Z","signature_b64":"cWW3OIPAkpRsIWucl+l/duMJw0nn/swrBKKEZKvSrrVWQljM7fn+EpbJpD8zO4nkpIygY2TqhprHUtnqT2/ABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"484bb8d06269c3b35a9188406d0ef0f81f2f3c27923edc4ed8add6e12b8961f8","last_reissued_at":"2026-07-05T03:07:02.742633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:02.742633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Trevor Darrell, Xiaolong Wang, Yinbo Chen, Zhuang Liu","submitted_at":"2020-03-09T20:06:36Z","abstract_excerpt":"Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective consistent with the testing objective. However, some recent works report that by training for whole-classification, i.e. classification on the whole label-set, it can get comparable or even better embedding than many meta-learning algorithms. The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04390","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/2003.04390/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":"2003.04390","created_at":"2026-07-05T03:07:02.742689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04390v4","created_at":"2026-07-05T03:07:02.742689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04390","created_at":"2026-07-05T03:07:02.742689+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBF3RUDCNHB3","created_at":"2026-07-05T03:07:02.742689+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBF3RUDCNHB3GWUR","created_at":"2026-07-05T03:07:02.742689+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBF3RUDC","created_at":"2026-07-05T03:07:02.742689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14145","citing_title":"Rethinking the Good Enough Embedding for Easy Few-Shot Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A","json":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A.json","graph_json":"https://pith.science/api/pith-number/JBF3RUDCNHB3GWURRBAG2DXQ7A/graph.json","events_json":"https://pith.science/api/pith-number/JBF3RUDCNHB3GWURRBAG2DXQ7A/events.json","paper":"https://pith.science/paper/JBF3RUDC"},"agent_actions":{"view_html":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A","download_json":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A.json","view_paper":"https://pith.science/paper/JBF3RUDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04390&json=true","fetch_graph":"https://pith.science/api/pith-number/JBF3RUDCNHB3GWURRBAG2DXQ7A/graph.json","fetch_events":"https://pith.science/api/pith-number/JBF3RUDCNHB3GWURRBAG2DXQ7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A/action/storage_attestation","attest_author":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A/action/author_attestation","sign_citation":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A/action/citation_signature","submit_replication":"https://pith.science/pith/JBF3RUDCNHB3GWURRBAG2DXQ7A/action/replication_record"}},"created_at":"2026-07-05T03:07:02.742689+00:00","updated_at":"2026-07-05T03:07:02.742689+00:00"}