{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7DELEEZD5QS2D3HQ4HPYXPI2G3","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":"e81f5c3958f5537f8d410c9b06e0797fbe8ee43981985082bba05d854c6a9636","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T01:57:33Z","title_canon_sha256":"d62b0ef7d07ba2d73a1e1a0a643e173ef33f15fe44dd0d8e761e60c1360a5c47"},"schema_version":"1.0","source":{"id":"2305.01855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01855","created_at":"2026-07-05T07:11:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01855v1","created_at":"2026-07-05T07:11:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01855","created_at":"2026-07-05T07:11:55Z"},{"alias_kind":"pith_short_12","alias_value":"7DELEEZD5QS2","created_at":"2026-07-05T07:11:55Z"},{"alias_kind":"pith_short_16","alias_value":"7DELEEZD5QS2D3HQ","created_at":"2026-07-05T07:11:55Z"},{"alias_kind":"pith_short_8","alias_value":"7DELEEZD","created_at":"2026-07-05T07:11:55Z"}],"graph_snapshots":[{"event_id":"sha256:250d78b69b7ac28b8f1a1f4b8580f4ed107450e60431c5b9fcda613f5bc01c61","target":"graph","created_at":"2026-07-05T07:11:55Z","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/2305.01855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning, an important vision-language task, often requires a tremendous number of finely labeled image-caption pairs for learning the underlying alignment between images and texts. In this paper, we proposed a multimodal data augmentation method, leveraging a recent text-to-image model called Stable Diffusion, to expand the training set via high-quality generation of image-caption pairs. Extensive experiments on the MS COCO dataset demonstrate the advantages of our approach over several benchmark methods, and particularly a significant boost when having fewer training instances. In ad","authors_text":"Changrong Xiao, Kunpeng Zhang, Sean Xin Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T01:57:33Z","title":"Multimodal Data Augmentation for Image Captioning using Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01855","kind":"arxiv","version":1},"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:c4c7ce8abd188ef791a4ea0bbc5932413f11afa52fce14c30e7938ab04953cae","target":"record","created_at":"2026-07-05T07:11:55Z","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":"e81f5c3958f5537f8d410c9b06e0797fbe8ee43981985082bba05d854c6a9636","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T01:57:33Z","title_canon_sha256":"d62b0ef7d07ba2d73a1e1a0a643e173ef33f15fe44dd0d8e761e60c1360a5c47"},"schema_version":"1.0","source":{"id":"2305.01855","kind":"arxiv","version":1}},"canonical_sha256":"f8c8b21323ec25a1ecf0e1df8bbd1a36f0bc45cf1696b7d7ebb4e0f7e48f7ff8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8c8b21323ec25a1ecf0e1df8bbd1a36f0bc45cf1696b7d7ebb4e0f7e48f7ff8","first_computed_at":"2026-07-05T07:11:55.571293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:55.571293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dcL5XMRlsusg5ND45ugUiRTcZp919P9Viu/wgRwIohKqoxdpTnkaBSyIvtPo33LHIm95ChTMOxop+23h5Ca/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:55.571772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4c7ce8abd188ef791a4ea0bbc5932413f11afa52fce14c30e7938ab04953cae","sha256:250d78b69b7ac28b8f1a1f4b8580f4ed107450e60431c5b9fcda613f5bc01c61"],"state_sha256":"22103833e1fe04d4fc3d65690fe65829004c6a98b3a935648e959fc5f3d12c85"}