{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YHM67GERBP2H43DTVJNYT27HUS","short_pith_number":"pith:YHM67GER","schema_version":"1.0","canonical_sha256":"c1d9ef98910bf47e6c73aa5b89ebe7a4b5048c091f1db6a374ad8c9cc8e30d81","source":{"kind":"arxiv","id":"2205.08728","version":2},"attestation_state":"computed","paper":{"title":"RandoMix: A mixed sample data augmentation method with multiple mixed modes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhai Nie, Furao Shen, Jian Zhao, Xiaoliang Liu","submitted_at":"2022-05-18T05:31:36Z","abstract_excerpt":"Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask-mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our resu"},"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":"2205.08728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-18T05:31:36Z","cross_cats_sorted":[],"title_canon_sha256":"3ae065f97f6f8c36c0ab37caaf5ab8df0eb1d35573cdf0d372c07f271d57967d","abstract_canon_sha256":"2d323230318cdfd80afd38f86f74d1edde78b33deb67740f92400eeb7609e90e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:22.910165Z","signature_b64":"TegmiNgN1FWMmodFNI4M2DTML5FC3N2BqirUVlNBoUTqyOqOwN860LsLD+OvITW6QS8+uQCkyiHzvnEiu1yMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1d9ef98910bf47e6c73aa5b89ebe7a4b5048c091f1db6a374ad8c9cc8e30d81","last_reissued_at":"2026-07-05T07:18:22.909754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:22.909754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RandoMix: A mixed sample data augmentation method with multiple mixed modes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhai Nie, Furao Shen, Jian Zhao, Xiaoliang Liu","submitted_at":"2022-05-18T05:31:36Z","abstract_excerpt":"Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask-mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08728","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/2205.08728/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":"2205.08728","created_at":"2026-07-05T07:18:22.909806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08728v2","created_at":"2026-07-05T07:18:22.909806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08728","created_at":"2026-07-05T07:18:22.909806+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHM67GERBP2H","created_at":"2026-07-05T07:18:22.909806+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHM67GERBP2H43DT","created_at":"2026-07-05T07:18:22.909806+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHM67GER","created_at":"2026-07-05T07:18:22.909806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15511","citing_title":"RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS","json":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS.json","graph_json":"https://pith.science/api/pith-number/YHM67GERBP2H43DTVJNYT27HUS/graph.json","events_json":"https://pith.science/api/pith-number/YHM67GERBP2H43DTVJNYT27HUS/events.json","paper":"https://pith.science/paper/YHM67GER"},"agent_actions":{"view_html":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS","download_json":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS.json","view_paper":"https://pith.science/paper/YHM67GER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08728&json=true","fetch_graph":"https://pith.science/api/pith-number/YHM67GERBP2H43DTVJNYT27HUS/graph.json","fetch_events":"https://pith.science/api/pith-number/YHM67GERBP2H43DTVJNYT27HUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS/action/storage_attestation","attest_author":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS/action/author_attestation","sign_citation":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS/action/citation_signature","submit_replication":"https://pith.science/pith/YHM67GERBP2H43DTVJNYT27HUS/action/replication_record"}},"created_at":"2026-07-05T07:18:22.909806+00:00","updated_at":"2026-07-05T07:18:22.909806+00:00"}