{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XCNSCARC756BEHCMMJUMHTHAYE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"73759c959e43970ea422df14891b2909ba9b00f2a09b58378255a31a5547f9af","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T17:58:09Z","title_canon_sha256":"6aa7278e3ac5c786016bad3811d05104c64c65d7a010078c77c77294a912de00"},"schema_version":"1.0","source":{"id":"2206.08358","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08358","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08358v3","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08358","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"XCNSCARC756B","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"XCNSCARC756BEHCM","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"XCNSCARC","created_at":"2026-07-05T05:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:92d9dee90c55fa11f160165022f51ae5a30b067f7d7db6ea18789defd9158954","target":"graph","created_at":"2026-07-05T05:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.08358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aston Zhang, Bo Li, Mu Li, Srikar Appalaraju, Wanqian Zhang, Xiaoshuai Hao, Yi Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T17:58:09Z","title":"MixGen: A New Multi-Modal Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08358","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:19a6b183bc260f37ec84574b239abf9188fa92ed7633372018e13fa376917c35","target":"record","created_at":"2026-07-05T05:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"73759c959e43970ea422df14891b2909ba9b00f2a09b58378255a31a5547f9af","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T17:58:09Z","title_canon_sha256":"6aa7278e3ac5c786016bad3811d05104c64c65d7a010078c77c77294a912de00"},"schema_version":"1.0","source":{"id":"2206.08358","kind":"arxiv","version":3}},"canonical_sha256":"b89b210222ff7c121c4c6268c3cce0c13b3fb0e793babac9efc361f621093a35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b89b210222ff7c121c4c6268c3cce0c13b3fb0e793babac9efc361f621093a35","first_computed_at":"2026-07-05T05:31:50.492056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:50.492056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6+oedJnNIUG7JFQPAZFXLZygErZlD54KQvNh1T64qeJp8yfYtfJaTScx9obJ9FQTOv24atfmAvNtOIVMt55PAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:50.492501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08358","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19a6b183bc260f37ec84574b239abf9188fa92ed7633372018e13fa376917c35","sha256:92d9dee90c55fa11f160165022f51ae5a30b067f7d7db6ea18789defd9158954"],"state_sha256":"eb1cf168928fa03c6e9fc6c9ee7536f3d33470d2fbab93b82c39c0d88a7c2e33"}