{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTX3VHABQ3DQ5URVM3HRWLCUI2","short_pith_number":"pith:JTX3VHAB","schema_version":"1.0","canonical_sha256":"4cefba9c0186c70ed23566cf1b2c5446b9be31117fb8d0270dacb499f7d63b36","source":{"kind":"arxiv","id":"2403.03472","version":1},"attestation_state":"computed","paper":{"title":"Boosting Meta-Training with Base Class Information for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Di He, Guodong Liu, Kun He, Weihao Jiang","submitted_at":"2024-03-06T05:13:23Z","abstract_excerpt":"Few-shot learning, a challenging task in machine learning, aims to learn a classifier adaptable to recognize new, unseen classes with limited labeled examples. Meta-learning has emerged as a prominent framework for few-shot learning. Its training framework is originally a task-level learning method, such as Model-Agnostic Meta-Learning (MAML) and Prototypical Networks. And a recently proposed training paradigm called Meta-Baseline, which consists of sequential pre-training and meta-training stages, gains state-of-the-art performance. However, as a non-end-to-end training method, indicating the"},"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":"2403.03472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T05:13:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ce513235d0791baf77b527f55b5a0aa2b9d08ecefad1c81cdf58f64beac8ac2c","abstract_canon_sha256":"59c5bd7f82deebd34c54c23e9653c7a682997f772473910f80ed6413b2ede043"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:48.682426Z","signature_b64":"0MDIc/rs1wBuQqGZHsAzcRoBL0sAn9RL+Af+/cCDOcCYcqUrGvXFGRhRxl6+JZVjtCWRr02UgMF1XzhyQ9dxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cefba9c0186c70ed23566cf1b2c5446b9be31117fb8d0270dacb499f7d63b36","last_reissued_at":"2026-07-05T07:52:48.681946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:48.681946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Meta-Training with Base Class Information for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Di He, Guodong Liu, Kun He, Weihao Jiang","submitted_at":"2024-03-06T05:13:23Z","abstract_excerpt":"Few-shot learning, a challenging task in machine learning, aims to learn a classifier adaptable to recognize new, unseen classes with limited labeled examples. Meta-learning has emerged as a prominent framework for few-shot learning. Its training framework is originally a task-level learning method, such as Model-Agnostic Meta-Learning (MAML) and Prototypical Networks. And a recently proposed training paradigm called Meta-Baseline, which consists of sequential pre-training and meta-training stages, gains state-of-the-art performance. However, as a non-end-to-end training method, indicating the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03472","kind":"arxiv","version":1},"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/2403.03472/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":"2403.03472","created_at":"2026-07-05T07:52:48.682008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03472v1","created_at":"2026-07-05T07:52:48.682008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03472","created_at":"2026-07-05T07:52:48.682008+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTX3VHABQ3DQ","created_at":"2026-07-05T07:52:48.682008+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTX3VHABQ3DQ5URV","created_at":"2026-07-05T07:52:48.682008+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTX3VHAB","created_at":"2026-07-05T07:52:48.682008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11758","citing_title":"Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2","json":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2.json","graph_json":"https://pith.science/api/pith-number/JTX3VHABQ3DQ5URVM3HRWLCUI2/graph.json","events_json":"https://pith.science/api/pith-number/JTX3VHABQ3DQ5URVM3HRWLCUI2/events.json","paper":"https://pith.science/paper/JTX3VHAB"},"agent_actions":{"view_html":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2","download_json":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2.json","view_paper":"https://pith.science/paper/JTX3VHAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03472&json=true","fetch_graph":"https://pith.science/api/pith-number/JTX3VHABQ3DQ5URVM3HRWLCUI2/graph.json","fetch_events":"https://pith.science/api/pith-number/JTX3VHABQ3DQ5URVM3HRWLCUI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2/action/storage_attestation","attest_author":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2/action/author_attestation","sign_citation":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2/action/citation_signature","submit_replication":"https://pith.science/pith/JTX3VHABQ3DQ5URVM3HRWLCUI2/action/replication_record"}},"created_at":"2026-07-05T07:52:48.682008+00:00","updated_at":"2026-07-05T07:52:48.682008+00:00"}