{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFQFQYEFHF5TO5GUFFGV7AM6HB","short_pith_number":"pith:XFQFQYEF","schema_version":"1.0","canonical_sha256":"b960586085397b3774d4294d5f819e385b3883ca709e1b4c15e328f334261e4e","source":{"kind":"arxiv","id":"2412.05722","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongjie Cheng, Haoyu Wang, Huahui Yi, Kang Li, Qicheng Lao, Yuting Shao, Zhiyuan Fan, Ziyuan Qin","submitted_at":"2024-12-07T18:44:38Z","abstract_excerpt":"Contemporary Text-to-Image (T2I) models frequently depend on qualitative human evaluations to assess the consistency between synthesized images and the text prompts. There is a demand for quantitative and automatic evaluation tools, given that human evaluation lacks reproducibility. We believe that an effective T2I evaluation metric should accomplish the following: detect instances where the generated images do not align with the textual prompts, a discrepancy we define as the `hallucination problem' in T2I tasks; record the types and frequency of hallucination issues, aiding users in understa"},"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":"2412.05722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-07T18:44:38Z","cross_cats_sorted":[],"title_canon_sha256":"3024bbfbfc764f020e2a848e0d69f01aaec5e508536744d54f8db224f409b8ed","abstract_canon_sha256":"0cf3c85d47d1957eff53afb56661f5a99cd6fca4737ec4866639f1d4d1ac790f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:07.882797Z","signature_b64":"iDz+rS4OMIDuSAF8YjwXpYKYb68LXgwTG/tsJzNb8+m6S8F+OHvzIbksP4hCpf947eKiaKmvAMJoYgKmXhAECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b960586085397b3774d4294d5f819e385b3883ca709e1b4c15e328f334261e4e","last_reissued_at":"2026-07-05T09:46:07.882322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:07.882322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongjie Cheng, Haoyu Wang, Huahui Yi, Kang Li, Qicheng Lao, Yuting Shao, Zhiyuan Fan, Ziyuan Qin","submitted_at":"2024-12-07T18:44:38Z","abstract_excerpt":"Contemporary Text-to-Image (T2I) models frequently depend on qualitative human evaluations to assess the consistency between synthesized images and the text prompts. There is a demand for quantitative and automatic evaluation tools, given that human evaluation lacks reproducibility. We believe that an effective T2I evaluation metric should accomplish the following: detect instances where the generated images do not align with the textual prompts, a discrepancy we define as the `hallucination problem' in T2I tasks; record the types and frequency of hallucination issues, aiding users in understa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05722","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/2412.05722/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":"2412.05722","created_at":"2026-07-05T09:46:07.882381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05722v1","created_at":"2026-07-05T09:46:07.882381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05722","created_at":"2026-07-05T09:46:07.882381+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFQFQYEFHF5T","created_at":"2026-07-05T09:46:07.882381+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFQFQYEFHF5TO5GU","created_at":"2026-07-05T09:46:07.882381+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFQFQYEF","created_at":"2026-07-05T09:46:07.882381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09666","citing_title":"Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB","json":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB.json","graph_json":"https://pith.science/api/pith-number/XFQFQYEFHF5TO5GUFFGV7AM6HB/graph.json","events_json":"https://pith.science/api/pith-number/XFQFQYEFHF5TO5GUFFGV7AM6HB/events.json","paper":"https://pith.science/paper/XFQFQYEF"},"agent_actions":{"view_html":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB","download_json":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB.json","view_paper":"https://pith.science/paper/XFQFQYEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05722&json=true","fetch_graph":"https://pith.science/api/pith-number/XFQFQYEFHF5TO5GUFFGV7AM6HB/graph.json","fetch_events":"https://pith.science/api/pith-number/XFQFQYEFHF5TO5GUFFGV7AM6HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB/action/storage_attestation","attest_author":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB/action/author_attestation","sign_citation":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB/action/citation_signature","submit_replication":"https://pith.science/pith/XFQFQYEFHF5TO5GUFFGV7AM6HB/action/replication_record"}},"created_at":"2026-07-05T09:46:07.882381+00:00","updated_at":"2026-07-05T09:46:07.882381+00:00"}