{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RZXWZVOHWOVYMMNHAAO4STOULR","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":"fa84106a2fa32c912cf8a07135195259e02d93c0e7747447cd599a7296f9b071","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T12:02:24Z","title_canon_sha256":"298d5dccaaa86e9b045597d9c60623cc3383cf20a0e10b7f628f4f006ae595ff"},"schema_version":"1.0","source":{"id":"2312.08846","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08846","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08846v4","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08846","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_12","alias_value":"RZXWZVOHWOVY","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_16","alias_value":"RZXWZVOHWOVYMMNH","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_8","alias_value":"RZXWZVOH","created_at":"2026-07-05T07:48:51Z"}],"graph_snapshots":[{"event_id":"sha256:d39e0fa16275f7eb36e0c10a8cbfa472e878e78107180410bfc799bc81699841","target":"graph","created_at":"2026-07-05T07:48:51Z","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/2312.08846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up training data volume in SMCL presents considerable obstacles in terms of computational cost and data inefficiency. To improve data efficiency in VLP, we propose Text-aware Image Mixing (TiMix), which integrates mix-based data augmentation techniques into SMCL, yielding significant performance improvements without significantly increasing computational overhe","authors_text":"Chaoya Jiang, Haiyang Xu, Ji Zhang, Ming Yan, Qinghao Ye, Shikun Zhang, Wei Ye","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T12:02:24Z","title":"TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08846","kind":"arxiv","version":4},"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":"sha256:2fc834a242aa752ac6ccaff02d5d11d0c57e9f39b382cdd4516f98e1336809b5","target":"record","created_at":"2026-07-05T07:48:51Z","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":"fa84106a2fa32c912cf8a07135195259e02d93c0e7747447cd599a7296f9b071","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T12:02:24Z","title_canon_sha256":"298d5dccaaa86e9b045597d9c60623cc3383cf20a0e10b7f628f4f006ae595ff"},"schema_version":"1.0","source":{"id":"2312.08846","kind":"arxiv","version":4}},"canonical_sha256":"8e6f6cd5c7b3ab8631a7001dc94dd45c500871cae2b6400089bbf2f01f60ef88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e6f6cd5c7b3ab8631a7001dc94dd45c500871cae2b6400089bbf2f01f60ef88","first_computed_at":"2026-07-05T07:48:51.119639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:51.119639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bh5I4Lp8TD8vUf8EhpOOcQh91uSy8g51YoQh8dQ1t5aKKGfCv7X51yhPIx2sg44X5G6rLt2TdVMNzhsNdzboCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:51.120062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08846","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fc834a242aa752ac6ccaff02d5d11d0c57e9f39b382cdd4516f98e1336809b5","sha256:d39e0fa16275f7eb36e0c10a8cbfa472e878e78107180410bfc799bc81699841"],"state_sha256":"34b63e411ded1282dc4d0fe618fe84877a965dd08de0026a615d6921e6438674"}