{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UL73URDI4WZ5UIF4FA2G4QMRBY","short_pith_number":"pith:UL73URDI","schema_version":"1.0","canonical_sha256":"a2ffba4468e5b3da20bc28346e41910e0b207f704a8e0d7d9c2a67fffb3ca89a","source":{"kind":"arxiv","id":"2009.13735","version":2},"attestation_state":"computed","paper":{"title":"MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianping Wang, Qing Li, Tom Ko, Yangbin Chen, Yun Ma","submitted_at":"2020-09-29T02:44:13Z","abstract_excerpt":"Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt quickly to new tasks. However, current MAML-based algorithms have limitations in forming generalizable decision boundaries. In this paper, we propose an approach called MetaMix. It generates virtual feature-target pairs within each episode to regularize the backbone models. MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boun"},"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":"2009.13735","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-29T02:44:13Z","cross_cats_sorted":[],"title_canon_sha256":"c4415dccd21070f27762589e49739bdf9d4681f305b07fad352bf47fcc7501ab","abstract_canon_sha256":"16f7ef68ff0c6a9a2f2731629fb171ee65b3ca94528abd527ded0091ecf1f356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:57.597651Z","signature_b64":"XNRYoHGRuO26Ll/fsmy1yzj828XyxEZboi1P8pTMgOuEeyrUTsmSEca9J1RZGh00LwQ4foRWiWysBypDnrKhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ffba4468e5b3da20bc28346e41910e0b207f704a8e0d7d9c2a67fffb3ca89a","last_reissued_at":"2026-07-05T01:41:57.597299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:57.597299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianping Wang, Qing Li, Tom Ko, Yangbin Chen, Yun Ma","submitted_at":"2020-09-29T02:44:13Z","abstract_excerpt":"Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt quickly to new tasks. However, current MAML-based algorithms have limitations in forming generalizable decision boundaries. In this paper, we propose an approach called MetaMix. It generates virtual feature-target pairs within each episode to regularize the backbone models. MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13735","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/2009.13735/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":"2009.13735","created_at":"2026-07-05T01:41:57.597362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13735v2","created_at":"2026-07-05T01:41:57.597362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13735","created_at":"2026-07-05T01:41:57.597362+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL73URDI4WZ5","created_at":"2026-07-05T01:41:57.597362+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL73URDI4WZ5UIF4","created_at":"2026-07-05T01:41:57.597362+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL73URDI","created_at":"2026-07-05T01:41:57.597362+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/UL73URDI4WZ5UIF4FA2G4QMRBY","json":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY.json","graph_json":"https://pith.science/api/pith-number/UL73URDI4WZ5UIF4FA2G4QMRBY/graph.json","events_json":"https://pith.science/api/pith-number/UL73URDI4WZ5UIF4FA2G4QMRBY/events.json","paper":"https://pith.science/paper/UL73URDI"},"agent_actions":{"view_html":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY","download_json":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY.json","view_paper":"https://pith.science/paper/UL73URDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13735&json=true","fetch_graph":"https://pith.science/api/pith-number/UL73URDI4WZ5UIF4FA2G4QMRBY/graph.json","fetch_events":"https://pith.science/api/pith-number/UL73URDI4WZ5UIF4FA2G4QMRBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY/action/storage_attestation","attest_author":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY/action/author_attestation","sign_citation":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY/action/citation_signature","submit_replication":"https://pith.science/pith/UL73URDI4WZ5UIF4FA2G4QMRBY/action/replication_record"}},"created_at":"2026-07-05T01:41:57.597362+00:00","updated_at":"2026-07-05T01:41:57.597362+00:00"}