{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N7VYYNQUFQCXVAZJCEGP2QWFK5","short_pith_number":"pith:N7VYYNQU","schema_version":"1.0","canonical_sha256":"6feb8c36142c057a8329110cfd42c5576638b79bf560780741d91dd43c52259a","source":{"kind":"arxiv","id":"2004.05805","version":2},"attestation_state":"computed","paper":{"title":"Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tiexin Qin, Wenbin Li, Yang Gao, Yinghuan Shi","submitted_at":"2020-04-13T07:41:56Z","abstract_excerpt":"Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled auxiliary set to train their models in an episodic-training paradigm. Such a kind of supervised setting basically limits the widespread use of few-shot learning algorithms. Instead, in this paper, we develop a novel framework called Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation (ULDA), which pays attention to the distribution diversity inside ea"},"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":"2004.05805","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T07:41:56Z","cross_cats_sorted":[],"title_canon_sha256":"69dfc19e6c0ba51753955a61b06209d02ea86a34725ed931e3ca2aba0f4afe75","abstract_canon_sha256":"808da2273dad9a05b846bc20027af18d13ef497e594d5c8561cb02a3d588d961"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:57.668891Z","signature_b64":"KPs6t7IhLj2hPXDeVVhEFwMQUM2LEA0s7P+rayfg+2QaJw7zG6baB9vUvQX7WuYbUKp7FpaYjoMVcP0OplYjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6feb8c36142c057a8329110cfd42c5576638b79bf560780741d91dd43c52259a","last_reissued_at":"2026-07-05T01:35:57.668493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:57.668493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tiexin Qin, Wenbin Li, Yang Gao, Yinghuan Shi","submitted_at":"2020-04-13T07:41:56Z","abstract_excerpt":"Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled auxiliary set to train their models in an episodic-training paradigm. Such a kind of supervised setting basically limits the widespread use of few-shot learning algorithms. Instead, in this paper, we develop a novel framework called Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation (ULDA), which pays attention to the distribution diversity inside ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05805","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/2004.05805/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":"2004.05805","created_at":"2026-07-05T01:35:57.668549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05805v2","created_at":"2026-07-05T01:35:57.668549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05805","created_at":"2026-07-05T01:35:57.668549+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7VYYNQUFQCX","created_at":"2026-07-05T01:35:57.668549+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7VYYNQUFQCXVAZJ","created_at":"2026-07-05T01:35:57.668549+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7VYYNQU","created_at":"2026-07-05T01:35:57.668549+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/N7VYYNQUFQCXVAZJCEGP2QWFK5","json":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5.json","graph_json":"https://pith.science/api/pith-number/N7VYYNQUFQCXVAZJCEGP2QWFK5/graph.json","events_json":"https://pith.science/api/pith-number/N7VYYNQUFQCXVAZJCEGP2QWFK5/events.json","paper":"https://pith.science/paper/N7VYYNQU"},"agent_actions":{"view_html":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5","download_json":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5.json","view_paper":"https://pith.science/paper/N7VYYNQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05805&json=true","fetch_graph":"https://pith.science/api/pith-number/N7VYYNQUFQCXVAZJCEGP2QWFK5/graph.json","fetch_events":"https://pith.science/api/pith-number/N7VYYNQUFQCXVAZJCEGP2QWFK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5/action/storage_attestation","attest_author":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5/action/author_attestation","sign_citation":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5/action/citation_signature","submit_replication":"https://pith.science/pith/N7VYYNQUFQCXVAZJCEGP2QWFK5/action/replication_record"}},"created_at":"2026-07-05T01:35:57.668549+00:00","updated_at":"2026-07-05T01:35:57.668549+00:00"}