{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7DELEEZD5QS2D3HQ4HPYXPI2G3","short_pith_number":"pith:7DELEEZD","schema_version":"1.0","canonical_sha256":"f8c8b21323ec25a1ecf0e1df8bbd1a36f0bc45cf1696b7d7ebb4e0f7e48f7ff8","source":{"kind":"arxiv","id":"2305.01855","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Data Augmentation for Image Captioning using Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changrong Xiao, Kunpeng Zhang, Sean Xin Xu","submitted_at":"2023-05-03T01:57:33Z","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"},"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":"2305.01855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T01:57:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d62b0ef7d07ba2d73a1e1a0a643e173ef33f15fe44dd0d8e761e60c1360a5c47","abstract_canon_sha256":"e81f5c3958f5537f8d410c9b06e0797fbe8ee43981985082bba05d854c6a9636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:55.571772Z","signature_b64":"dcL5XMRlsusg5ND45ugUiRTcZp919P9Viu/wgRwIohKqoxdpTnkaBSyIvtPo33LHIm95ChTMOxop+23h5Ca/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c8b21323ec25a1ecf0e1df8bbd1a36f0bc45cf1696b7d7ebb4e0f7e48f7ff8","last_reissued_at":"2026-07-05T07:11:55.571293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:55.571293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Data Augmentation for Image Captioning using Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changrong Xiao, Kunpeng Zhang, Sean Xin Xu","submitted_at":"2023-05-03T01:57:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01855","kind":"arxiv","version":1},"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/2305.01855/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":"2305.01855","created_at":"2026-07-05T07:11:55.571357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01855v1","created_at":"2026-07-05T07:11:55.571357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01855","created_at":"2026-07-05T07:11:55.571357+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DELEEZD5QS2","created_at":"2026-07-05T07:11:55.571357+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DELEEZD5QS2D3HQ","created_at":"2026-07-05T07:11:55.571357+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DELEEZD","created_at":"2026-07-05T07:11:55.571357+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/7DELEEZD5QS2D3HQ4HPYXPI2G3","json":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3.json","graph_json":"https://pith.science/api/pith-number/7DELEEZD5QS2D3HQ4HPYXPI2G3/graph.json","events_json":"https://pith.science/api/pith-number/7DELEEZD5QS2D3HQ4HPYXPI2G3/events.json","paper":"https://pith.science/paper/7DELEEZD"},"agent_actions":{"view_html":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3","download_json":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3.json","view_paper":"https://pith.science/paper/7DELEEZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01855&json=true","fetch_graph":"https://pith.science/api/pith-number/7DELEEZD5QS2D3HQ4HPYXPI2G3/graph.json","fetch_events":"https://pith.science/api/pith-number/7DELEEZD5QS2D3HQ4HPYXPI2G3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3/action/storage_attestation","attest_author":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3/action/author_attestation","sign_citation":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3/action/citation_signature","submit_replication":"https://pith.science/pith/7DELEEZD5QS2D3HQ4HPYXPI2G3/action/replication_record"}},"created_at":"2026-07-05T07:11:55.571357+00:00","updated_at":"2026-07-05T07:11:55.571357+00:00"}