{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3MCRF47C3UVPNDONWQELAMMPRF","short_pith_number":"pith:3MCRF47C","schema_version":"1.0","canonical_sha256":"db0512f3e2dd2af68dcdb408b0318f8969a0f077da113b45d74e5343f4e904fb","source":{"kind":"arxiv","id":"2410.11824","version":2},"attestation_state":"computed","paper":{"title":"KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaurav Singh Tomar, Hagai Taitelbaum, Hexiang Hu, Hsin-Ping Huang, Kelvin C.K. Chan, Ming-Hsuan Yang, Ming-Wei Chang, Xinyi Wang, Xuhui Jia, Yonatan Bitton, Yu-Chuan Su","submitted_at":"2024-10-15T17:50:37Z","abstract_excerpt":"Recent advances in text-to-image generation have improved the quality of synthesized images, but evaluations mainly focus on aesthetics or alignment with text prompts. Thus, it remains unclear whether these models can accurately represent a wide variety of realistic visual entities. To bridge this gap, we propose KITTEN, a benchmark for Knowledge-InTensive image generaTion on real-world ENtities. Using KITTEN, we conduct a systematic study of the latest text-to-image models and retrieval-augmented models, focusing on their ability to generate real-world visual entities, such as landmarks and a"},"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":"2410.11824","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T17:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"57a3205f3a6b5ca369792fb09ed101ed927e99985bb32a75df66888b98eade3e","abstract_canon_sha256":"6cb64405def9cb2d38d6aba926b9550f4eecea15d3b4fc1cf56a26276ce50288"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:57.786343Z","signature_b64":"v0I++tTtsjdquLUHTOy0RZDXOaL85rkATxpHhRYJkQ4i3moLmKR63Z/Hhsp33L0qmTLDKdIix9r4KuAyk3+XCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db0512f3e2dd2af68dcdb408b0318f8969a0f077da113b45d74e5343f4e904fb","last_reissued_at":"2026-07-05T11:43:57.785817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:57.785817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaurav Singh Tomar, Hagai Taitelbaum, Hexiang Hu, Hsin-Ping Huang, Kelvin C.K. Chan, Ming-Hsuan Yang, Ming-Wei Chang, Xinyi Wang, Xuhui Jia, Yonatan Bitton, Yu-Chuan Su","submitted_at":"2024-10-15T17:50:37Z","abstract_excerpt":"Recent advances in text-to-image generation have improved the quality of synthesized images, but evaluations mainly focus on aesthetics or alignment with text prompts. Thus, it remains unclear whether these models can accurately represent a wide variety of realistic visual entities. To bridge this gap, we propose KITTEN, a benchmark for Knowledge-InTensive image generaTion on real-world ENtities. Using KITTEN, we conduct a systematic study of the latest text-to-image models and retrieval-augmented models, focusing on their ability to generate real-world visual entities, such as landmarks and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11824","kind":"arxiv","version":2},"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/2410.11824/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":"2410.11824","created_at":"2026-07-05T11:43:57.785882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11824v2","created_at":"2026-07-05T11:43:57.785882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11824","created_at":"2026-07-05T11:43:57.785882+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MCRF47C3UVP","created_at":"2026-07-05T11:43:57.785882+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MCRF47C3UVPNDON","created_at":"2026-07-05T11:43:57.785882+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MCRF47C","created_at":"2026-07-05T11:43:57.785882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04300","citing_title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF","json":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF.json","graph_json":"https://pith.science/api/pith-number/3MCRF47C3UVPNDONWQELAMMPRF/graph.json","events_json":"https://pith.science/api/pith-number/3MCRF47C3UVPNDONWQELAMMPRF/events.json","paper":"https://pith.science/paper/3MCRF47C"},"agent_actions":{"view_html":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF","download_json":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF.json","view_paper":"https://pith.science/paper/3MCRF47C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11824&json=true","fetch_graph":"https://pith.science/api/pith-number/3MCRF47C3UVPNDONWQELAMMPRF/graph.json","fetch_events":"https://pith.science/api/pith-number/3MCRF47C3UVPNDONWQELAMMPRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/action/storage_attestation","attest_author":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/action/author_attestation","sign_citation":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/action/citation_signature","submit_replication":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/action/replication_record"}},"created_at":"2026-07-05T11:43:57.785882+00:00","updated_at":"2026-07-05T11:43:57.785882+00:00"}