{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EE7JFLI2W32WETVTLSJCE2MM76","short_pith_number":"pith:EE7JFLI2","schema_version":"1.0","canonical_sha256":"213e92ad1ab6f5624eb35c9222698cff97009b20a5fc11bcc5f5867737ab7f1b","source":{"kind":"arxiv","id":"2212.10888","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chengtai Cao, Fan Zhou, Jianping Wang, Kunpeng Zhang, Yurou Dai","submitted_at":"2022-12-21T09:58:14Z","abstract_excerpt":"Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model's generalization by adding slightly disturbed versions of existing data or synthesizing new data. This survey comprehensively reviews a crucial subset of DA techniques, namely Mix-based Data Augmentation (MixDA), which generates novel samples by combining multiple examples. In contrast to traditional DA approaches that operate on single samples or entire datasets, MixDA stands out due to its effectiveness, simplicity, flexibili"},"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":"2212.10888","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T09:58:14Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"1672c3c5bfbf99de0d2b8586a820366e207dc88f416511a47e12e7c35cd20e65","abstract_canon_sha256":"6a6b35e669fa36ccc91b8be146318a774050b73bce15a10aeed6acb04f25d93e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:55.807865Z","signature_b64":"LzVINQ5R6bjOuv+ICGjKsJf2YOMtSxAdxzgiFcUnzzItT5021TsCJfAEQ7Ub1iUWoJtXaO65OGNaLNO/HIQmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213e92ad1ab6f5624eb35c9222698cff97009b20a5fc11bcc5f5867737ab7f1b","last_reissued_at":"2026-07-05T08:26:55.807425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:55.807425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chengtai Cao, Fan Zhou, Jianping Wang, Kunpeng Zhang, Yurou Dai","submitted_at":"2022-12-21T09:58:14Z","abstract_excerpt":"Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model's generalization by adding slightly disturbed versions of existing data or synthesizing new data. This survey comprehensively reviews a crucial subset of DA techniques, namely Mix-based Data Augmentation (MixDA), which generates novel samples by combining multiple examples. In contrast to traditional DA approaches that operate on single samples or entire datasets, MixDA stands out due to its effectiveness, simplicity, flexibili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10888","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/2212.10888/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":"2212.10888","created_at":"2026-07-05T08:26:55.807483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10888v2","created_at":"2026-07-05T08:26:55.807483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10888","created_at":"2026-07-05T08:26:55.807483+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE7JFLI2W32W","created_at":"2026-07-05T08:26:55.807483+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE7JFLI2W32WETVT","created_at":"2026-07-05T08:26:55.807483+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE7JFLI2","created_at":"2026-07-05T08:26:55.807483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22492","citing_title":"MTT-Bench: Predicting Social Dominance in Mice via Multimodal Large Language Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76","json":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76.json","graph_json":"https://pith.science/api/pith-number/EE7JFLI2W32WETVTLSJCE2MM76/graph.json","events_json":"https://pith.science/api/pith-number/EE7JFLI2W32WETVTLSJCE2MM76/events.json","paper":"https://pith.science/paper/EE7JFLI2"},"agent_actions":{"view_html":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76","download_json":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76.json","view_paper":"https://pith.science/paper/EE7JFLI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10888&json=true","fetch_graph":"https://pith.science/api/pith-number/EE7JFLI2W32WETVTLSJCE2MM76/graph.json","fetch_events":"https://pith.science/api/pith-number/EE7JFLI2W32WETVTLSJCE2MM76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76/action/storage_attestation","attest_author":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76/action/author_attestation","sign_citation":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76/action/citation_signature","submit_replication":"https://pith.science/pith/EE7JFLI2W32WETVTLSJCE2MM76/action/replication_record"}},"created_at":"2026-07-05T08:26:55.807483+00:00","updated_at":"2026-07-05T08:26:55.807483+00:00"}