{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:F4RAHCRWYOKD7NNMW5XERFVACI","short_pith_number":"pith:F4RAHCRW","schema_version":"1.0","canonical_sha256":"2f22038a36c3943fb5acb76e4896a0123bd31820978f7030d20a10c230ecd4f4","source":{"kind":"arxiv","id":"2209.08928","version":3},"attestation_state":"computed","paper":{"title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Changqing Zhang, Fan Yang, Jianhua Yao, Lanqing Li, Liu Liu, Peilin Zhao, Yatao Bian, Zhipeng Liang, Zongbo Han","submitted_at":"2022-09-19T11:22:28Z","abstract_excerpt":"Subpopulation shift widely exists in many real-world machine learning applications, referring to the training and test distributions containing the same subpopulation groups but varying in subpopulation frequencies. Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset. However, some recent studies have recognized that most of these approaches fail to improve the performance over empirical risk minimization especially when applied to over-parameterized neural networks. In this work"},"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":"2209.08928","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-19T11:22:28Z","cross_cats_sorted":[],"title_canon_sha256":"c315ee9a5fa1ac74586d8c67b1dde5fd2bf30c407654af42d28afb0101db98a7","abstract_canon_sha256":"7b283a08893fccef7b5e1237b576300da1f844f069e64932b769cdaba9dc442c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:54.382786Z","signature_b64":"2rSQMrEojbC9JVgJfH7EYdMzEGr8Ll9PNA9BX1aUJ1GUxNd9wrjQVHIQFV/BVIRTs6EeshvkO4mVOVtVSRxpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f22038a36c3943fb5acb76e4896a0123bd31820978f7030d20a10c230ecd4f4","last_reissued_at":"2026-07-05T05:29:54.382257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:54.382257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Changqing Zhang, Fan Yang, Jianhua Yao, Lanqing Li, Liu Liu, Peilin Zhao, Yatao Bian, Zhipeng Liang, Zongbo Han","submitted_at":"2022-09-19T11:22:28Z","abstract_excerpt":"Subpopulation shift widely exists in many real-world machine learning applications, referring to the training and test distributions containing the same subpopulation groups but varying in subpopulation frequencies. Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset. However, some recent studies have recognized that most of these approaches fail to improve the performance over empirical risk minimization especially when applied to over-parameterized neural networks. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08928","kind":"arxiv","version":3},"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/2209.08928/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":"2209.08928","created_at":"2026-07-05T05:29:54.382342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08928v3","created_at":"2026-07-05T05:29:54.382342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08928","created_at":"2026-07-05T05:29:54.382342+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4RAHCRWYOKD","created_at":"2026-07-05T05:29:54.382342+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4RAHCRWYOKD7NNM","created_at":"2026-07-05T05:29:54.382342+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4RAHCRW","created_at":"2026-07-05T05:29:54.382342+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/F4RAHCRWYOKD7NNMW5XERFVACI","json":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI.json","graph_json":"https://pith.science/api/pith-number/F4RAHCRWYOKD7NNMW5XERFVACI/graph.json","events_json":"https://pith.science/api/pith-number/F4RAHCRWYOKD7NNMW5XERFVACI/events.json","paper":"https://pith.science/paper/F4RAHCRW"},"agent_actions":{"view_html":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI","download_json":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI.json","view_paper":"https://pith.science/paper/F4RAHCRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08928&json=true","fetch_graph":"https://pith.science/api/pith-number/F4RAHCRWYOKD7NNMW5XERFVACI/graph.json","fetch_events":"https://pith.science/api/pith-number/F4RAHCRWYOKD7NNMW5XERFVACI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI/action/storage_attestation","attest_author":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI/action/author_attestation","sign_citation":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI/action/citation_signature","submit_replication":"https://pith.science/pith/F4RAHCRWYOKD7NNMW5XERFVACI/action/replication_record"}},"created_at":"2026-07-05T05:29:54.382342+00:00","updated_at":"2026-07-05T05:29:54.382342+00:00"}