{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XCNSCARC756BEHCMMJUMHTHAYE","short_pith_number":"pith:XCNSCARC","schema_version":"1.0","canonical_sha256":"b89b210222ff7c121c4c6268c3cce0c13b3fb0e793babac9efc361f621093a35","source":{"kind":"arxiv","id":"2206.08358","version":3},"attestation_state":"computed","paper":{"title":"MixGen: A New Multi-Modal Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aston Zhang, Bo Li, Mu Li, Srikar Appalaraju, Wanqian Zhang, Xiaoshuai Hao, Yi Zhu","submitted_at":"2022-06-16T17:58:09Z","abstract_excerpt":"Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data augmentation for vision-language representation learning to further improve data efficiency. It generates new image-text pairs with semantic relationships preserved by interpolating images and concatenating text. It's simple, and can be plug-and-played into existing pipelines. We evaluate MixGen on four architectures, including CLIP, ViLT, ALBEF and TCL, across five "},"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":"2206.08358","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T17:58:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6aa7278e3ac5c786016bad3811d05104c64c65d7a010078c77c77294a912de00","abstract_canon_sha256":"73759c959e43970ea422df14891b2909ba9b00f2a09b58378255a31a5547f9af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:50.492501Z","signature_b64":"6+oedJnNIUG7JFQPAZFXLZygErZlD54KQvNh1T64qeJp8yfYtfJaTScx9obJ9FQTOv24atfmAvNtOIVMt55PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b89b210222ff7c121c4c6268c3cce0c13b3fb0e793babac9efc361f621093a35","last_reissued_at":"2026-07-05T05:31:50.492056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:50.492056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixGen: A New Multi-Modal Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aston Zhang, Bo Li, Mu Li, Srikar Appalaraju, Wanqian Zhang, Xiaoshuai Hao, Yi Zhu","submitted_at":"2022-06-16T17:58:09Z","abstract_excerpt":"Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data augmentation for vision-language representation learning to further improve data efficiency. It generates new image-text pairs with semantic relationships preserved by interpolating images and concatenating text. It's simple, and can be plug-and-played into existing pipelines. We evaluate MixGen on four architectures, including CLIP, ViLT, ALBEF and TCL, across five "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08358","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/2206.08358/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":"2206.08358","created_at":"2026-07-05T05:31:50.492119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08358v3","created_at":"2026-07-05T05:31:50.492119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08358","created_at":"2026-07-05T05:31:50.492119+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCNSCARC756B","created_at":"2026-07-05T05:31:50.492119+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCNSCARC756BEHCM","created_at":"2026-07-05T05:31:50.492119+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCNSCARC","created_at":"2026-07-05T05:31:50.492119+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/XCNSCARC756BEHCMMJUMHTHAYE","json":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE.json","graph_json":"https://pith.science/api/pith-number/XCNSCARC756BEHCMMJUMHTHAYE/graph.json","events_json":"https://pith.science/api/pith-number/XCNSCARC756BEHCMMJUMHTHAYE/events.json","paper":"https://pith.science/paper/XCNSCARC"},"agent_actions":{"view_html":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE","download_json":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE.json","view_paper":"https://pith.science/paper/XCNSCARC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08358&json=true","fetch_graph":"https://pith.science/api/pith-number/XCNSCARC756BEHCMMJUMHTHAYE/graph.json","fetch_events":"https://pith.science/api/pith-number/XCNSCARC756BEHCMMJUMHTHAYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE/action/storage_attestation","attest_author":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE/action/author_attestation","sign_citation":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE/action/citation_signature","submit_replication":"https://pith.science/pith/XCNSCARC756BEHCMMJUMHTHAYE/action/replication_record"}},"created_at":"2026-07-05T05:31:50.492119+00:00","updated_at":"2026-07-05T05:31:50.492119+00:00"}