{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y5HNMFL7E7GNKDG356JTELU7KT","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":"cd5386af4e7eccfcedfc605d19d59c8067d13371914c6d84e7368dfc59127c6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T08:53:37Z","title_canon_sha256":"a3b02d693f7491565c5cbdb97bcfc20f1863685f80f578a4610906d9ddb3b05f"},"schema_version":"1.0","source":{"id":"2412.19531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19531","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19531v1","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19531","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"Y5HNMFL7E7GN","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y5HNMFL7E7GNKDG3","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y5HNMFL7","created_at":"2026-07-05T09:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:79c8ec243eb1845dcd7c1be0090bd504abde416941cff85f402f95f4fa75dde6","target":"graph","created_at":"2026-07-05T09:54:37Z","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/2412.19531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit hallucination, generating descriptive content that deviates from the visual reality, the ramifications of such caption hallucinations on T2I generation performance remain under-explored. Through our empirical investigation, we first establish a comprehensive dataset comprising VLM-generated captions, and then systematically analyze how caption hallucination influences generation outcomes. Our findings reveal that (1) t","authors_text":"Jianyi Wang, Liangke Gui, Lu Jiang, Matt Fredrikson, Qi Zhao, Shanchuan Lin, Weichen Yu, Ziyan Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T08:53:37Z","title":"Is Your Text-to-Image Model Robust to Caption Noise?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19531","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":"sha256:08c76e185f383b11ff95b6c44141f42da9fe09f6df7187b29ab30933cc3f50ef","target":"record","created_at":"2026-07-05T09:54:37Z","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":"cd5386af4e7eccfcedfc605d19d59c8067d13371914c6d84e7368dfc59127c6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T08:53:37Z","title_canon_sha256":"a3b02d693f7491565c5cbdb97bcfc20f1863685f80f578a4610906d9ddb3b05f"},"schema_version":"1.0","source":{"id":"2412.19531","kind":"arxiv","version":1}},"canonical_sha256":"c74ed6157f27ccd50cdbef93322e9f54f1488cb5d7b9ceb10468741a1cb03cb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c74ed6157f27ccd50cdbef93322e9f54f1488cb5d7b9ceb10468741a1cb03cb0","first_computed_at":"2026-07-05T09:54:37.430551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:37.430551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7GHn2Ank1OD6R2MsNtg+NYkNMKpdpFHzXtWzVYHsqp3eVNEd0BgI9fGoacaTzE0xaV/26fQzqHOCv0sazkXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:37.431016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08c76e185f383b11ff95b6c44141f42da9fe09f6df7187b29ab30933cc3f50ef","sha256:79c8ec243eb1845dcd7c1be0090bd504abde416941cff85f402f95f4fa75dde6"],"state_sha256":"e8a214c7c76a0e81dc8cfaab758186e68cdf6a865a58df2e582aac617d376e6b"}