{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AQP2ZSCMPJW5LP3NK5C4QTUZ2B","short_pith_number":"pith:AQP2ZSCM","schema_version":"1.0","canonical_sha256":"041facc84c7a6dd5bf6d5745c84e99d05697ba5476b8411d4ef6504d119b6850","source":{"kind":"arxiv","id":"2211.15846","version":1},"attestation_state":"computed","paper":{"title":"LUMix: Improving Mixup by Better Modelling Label Uncertainty","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jie-Neng Chen, Philip Torr, Ruifei He, Shuyang Sun, Song Bai","submitted_at":"2022-11-29T00:47:55Z","abstract_excerpt":"Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentation to help avoid overfitting. Previous Mixup-based methods linearly combine images and labels to generate additional training data. However, this is problematic if the object does not occupy the whole image as we demonstrate in Figure 1. Correctly assigning the label weights is hard even for human beings and there is no clear criterion to measure it. To tackle this problem, in this paper, we propose LUMix, which model"},"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":"2211.15846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-29T00:47:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"71837979d6096e630c514fe0109602453152241d4bcfdd7e09b7d7304b13d16d","abstract_canon_sha256":"2de852a87c3a296b0b0aec1d85563c1a55cf39d34c9235a4b8fc2ca760f2d857"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:18.953535Z","signature_b64":"4i++xMQUKeOMltAKkQeJp5fI5dnUcEI36iNvmVQj/zshdjLbvZfUOhlxeZ5IprD8XG3KqtaqSjSj6fder6QMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041facc84c7a6dd5bf6d5745c84e99d05697ba5476b8411d4ef6504d119b6850","last_reissued_at":"2026-07-05T05:20:18.953030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:18.953030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LUMix: Improving Mixup by Better Modelling Label Uncertainty","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jie-Neng Chen, Philip Torr, Ruifei He, Shuyang Sun, Song Bai","submitted_at":"2022-11-29T00:47:55Z","abstract_excerpt":"Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentation to help avoid overfitting. Previous Mixup-based methods linearly combine images and labels to generate additional training data. However, this is problematic if the object does not occupy the whole image as we demonstrate in Figure 1. Correctly assigning the label weights is hard even for human beings and there is no clear criterion to measure it. To tackle this problem, in this paper, we propose LUMix, which model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15846","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/2211.15846/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":"2211.15846","created_at":"2026-07-05T05:20:18.953096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15846v1","created_at":"2026-07-05T05:20:18.953096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15846","created_at":"2026-07-05T05:20:18.953096+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQP2ZSCMPJW5","created_at":"2026-07-05T05:20:18.953096+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQP2ZSCMPJW5LP3N","created_at":"2026-07-05T05:20:18.953096+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQP2ZSCM","created_at":"2026-07-05T05:20:18.953096+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/AQP2ZSCMPJW5LP3NK5C4QTUZ2B","json":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B.json","graph_json":"https://pith.science/api/pith-number/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/graph.json","events_json":"https://pith.science/api/pith-number/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/events.json","paper":"https://pith.science/paper/AQP2ZSCM"},"agent_actions":{"view_html":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B","download_json":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B.json","view_paper":"https://pith.science/paper/AQP2ZSCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15846&json=true","fetch_graph":"https://pith.science/api/pith-number/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/graph.json","fetch_events":"https://pith.science/api/pith-number/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/action/storage_attestation","attest_author":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/action/author_attestation","sign_citation":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/action/citation_signature","submit_replication":"https://pith.science/pith/AQP2ZSCMPJW5LP3NK5C4QTUZ2B/action/replication_record"}},"created_at":"2026-07-05T05:20:18.953096+00:00","updated_at":"2026-07-05T05:20:18.953096+00:00"}