{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VJJMCWTUZI2NJLOOITVIOKJOVA","short_pith_number":"pith:VJJMCWTU","schema_version":"1.0","canonical_sha256":"aa52c15a74ca34d4adce44ea87292ea81841a7be15a5d8fe9f1abe5bd01d1872","source":{"kind":"arxiv","id":"2409.12784","version":7},"attestation_state":"computed","paper":{"title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hojun Choi, Hyunjung Shim, Youngsun Lim","submitted_at":"2024-09-19T13:51:21Z","abstract_excerpt":"Despite the impressive success of text-to-image (TTI) generation models, existing studies overlook the issue of whether these models accurately convey factual information. In this paper, we focus on the problem of image hallucination, where images created by generation models fail to faithfully depict factual content. To address this, we introduce I-HallA (Image Hallucination evaluation with Question Answering), a novel automated evaluation metric that measures the factuality of generated images through visual question answering (VQA). We also introduce I-HallA v1.0, a curated benchmark datase"},"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":"2409.12784","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T13:51:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72ce00b5b76d0e28dcd8c9652b7dd996be8d10709f4a13cba16b2b9b47cde6e5","abstract_canon_sha256":"2d74f020d21d3361b243b5ba2232494fdbf080ad8a6b1cf3476c91fe45443d89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:01.220223Z","signature_b64":"ylDHX21ssngE1aE4ih+0f4qZaHqBkOHIWVx2WNUcGxt4ksRWvdSxA3nnYKr58FE7hIfy3/Ui0Ycd7RAyK/woCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa52c15a74ca34d4adce44ea87292ea81841a7be15a5d8fe9f1abe5bd01d1872","last_reissued_at":"2026-07-05T10:12:01.219713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:01.219713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hojun Choi, Hyunjung Shim, Youngsun Lim","submitted_at":"2024-09-19T13:51:21Z","abstract_excerpt":"Despite the impressive success of text-to-image (TTI) generation models, existing studies overlook the issue of whether these models accurately convey factual information. In this paper, we focus on the problem of image hallucination, where images created by generation models fail to faithfully depict factual content. To address this, we introduce I-HallA (Image Hallucination evaluation with Question Answering), a novel automated evaluation metric that measures the factuality of generated images through visual question answering (VQA). We also introduce I-HallA v1.0, a curated benchmark datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12784","kind":"arxiv","version":7},"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/2409.12784/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":"2409.12784","created_at":"2026-07-05T10:12:01.219778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12784v7","created_at":"2026-07-05T10:12:01.219778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12784","created_at":"2026-07-05T10:12:01.219778+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJJMCWTUZI2N","created_at":"2026-07-05T10:12:01.219778+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJJMCWTUZI2NJLOO","created_at":"2026-07-05T10:12:01.219778+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJJMCWTU","created_at":"2026-07-05T10:12:01.219778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16154","citing_title":"On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA","json":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA.json","graph_json":"https://pith.science/api/pith-number/VJJMCWTUZI2NJLOOITVIOKJOVA/graph.json","events_json":"https://pith.science/api/pith-number/VJJMCWTUZI2NJLOOITVIOKJOVA/events.json","paper":"https://pith.science/paper/VJJMCWTU"},"agent_actions":{"view_html":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA","download_json":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA.json","view_paper":"https://pith.science/paper/VJJMCWTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12784&json=true","fetch_graph":"https://pith.science/api/pith-number/VJJMCWTUZI2NJLOOITVIOKJOVA/graph.json","fetch_events":"https://pith.science/api/pith-number/VJJMCWTUZI2NJLOOITVIOKJOVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA/action/storage_attestation","attest_author":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA/action/author_attestation","sign_citation":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA/action/citation_signature","submit_replication":"https://pith.science/pith/VJJMCWTUZI2NJLOOITVIOKJOVA/action/replication_record"}},"created_at":"2026-07-05T10:12:01.219778+00:00","updated_at":"2026-07-05T10:12:01.219778+00:00"}