{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FVFCISX3REL7MI3XWMYWHIFJIV","short_pith_number":"pith:FVFCISX3","schema_version":"1.0","canonical_sha256":"2d4a244afb8917f62377b33163a0a9456990c37ecdac93a4c2b7c0aff046af3d","source":{"kind":"arxiv","id":"2209.04851","version":3},"attestation_state":"computed","paper":{"title":"OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Tan, Di Wu, Juanxi Tian, Siyuan Li, Stan Z. Li, Weiyang Jin, Zedong Wang, Zicheng Liu","submitted_at":"2022-09-11T12:46:01Z","abstract_excerpt":"Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progress, resulting in poor reproducibility, unfair comparisons, and conflicting insights. In this paper, we introduce OpenMixup, the first mixup augmentation codebase, and benchmark for visual representation learning. Specifically, we train 18 representative mixup baselines from scratch and rigorously evaluate them across 11 image datasets of varying scales and granularity, ranging"},"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":"2209.04851","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-11T12:46:01Z","cross_cats_sorted":[],"title_canon_sha256":"be35afc97f01e2c700004ed5e557fe0d7181ac868cc421326da2ad9223e75ee7","abstract_canon_sha256":"b72a25fc41c3a615c3b23f9d488ff1a58da6b2ae740920549acdb4e18161be7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:05.801880Z","signature_b64":"jN7Us28APg0AWOgoIDKB2D8PMOkTqV5kWmHhCk8fZ8L4NHhuMTUBoppVWExH1m9Ky4fD6gqX+G97tfN7CBxeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d4a244afb8917f62377b33163a0a9456990c37ecdac93a4c2b7c0aff046af3d","last_reissued_at":"2026-07-05T09:16:05.801341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:05.801341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Tan, Di Wu, Juanxi Tian, Siyuan Li, Stan Z. Li, Weiyang Jin, Zedong Wang, Zicheng Liu","submitted_at":"2022-09-11T12:46:01Z","abstract_excerpt":"Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progress, resulting in poor reproducibility, unfair comparisons, and conflicting insights. In this paper, we introduce OpenMixup, the first mixup augmentation codebase, and benchmark for visual representation learning. Specifically, we train 18 representative mixup baselines from scratch and rigorously evaluate them across 11 image datasets of varying scales and granularity, ranging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04851","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/2209.04851/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":"2209.04851","created_at":"2026-07-05T09:16:05.801405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04851v3","created_at":"2026-07-05T09:16:05.801405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04851","created_at":"2026-07-05T09:16:05.801405+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVFCISX3REL7","created_at":"2026-07-05T09:16:05.801405+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVFCISX3REL7MI3X","created_at":"2026-07-05T09:16:05.801405+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVFCISX3","created_at":"2026-07-05T09:16:05.801405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22307","citing_title":"Enhancing Protein Representation Learning via Manifold Restore Mixing","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV","json":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV.json","graph_json":"https://pith.science/api/pith-number/FVFCISX3REL7MI3XWMYWHIFJIV/graph.json","events_json":"https://pith.science/api/pith-number/FVFCISX3REL7MI3XWMYWHIFJIV/events.json","paper":"https://pith.science/paper/FVFCISX3"},"agent_actions":{"view_html":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV","download_json":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV.json","view_paper":"https://pith.science/paper/FVFCISX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04851&json=true","fetch_graph":"https://pith.science/api/pith-number/FVFCISX3REL7MI3XWMYWHIFJIV/graph.json","fetch_events":"https://pith.science/api/pith-number/FVFCISX3REL7MI3XWMYWHIFJIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV/action/storage_attestation","attest_author":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV/action/author_attestation","sign_citation":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV/action/citation_signature","submit_replication":"https://pith.science/pith/FVFCISX3REL7MI3XWMYWHIFJIV/action/replication_record"}},"created_at":"2026-07-05T09:16:05.801405+00:00","updated_at":"2026-07-05T09:16:05.801405+00:00"}