{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3MCRF47C3UVPNDONWQELAMMPRF","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":"6cb64405def9cb2d38d6aba926b9550f4eecea15d3b4fc1cf56a26276ce50288","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T17:50:37Z","title_canon_sha256":"57a3205f3a6b5ca369792fb09ed101ed927e99985bb32a75df66888b98eade3e"},"schema_version":"1.0","source":{"id":"2410.11824","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11824","created_at":"2026-07-05T11:43:57Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11824v2","created_at":"2026-07-05T11:43:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11824","created_at":"2026-07-05T11:43:57Z"},{"alias_kind":"pith_short_12","alias_value":"3MCRF47C3UVP","created_at":"2026-07-05T11:43:57Z"},{"alias_kind":"pith_short_16","alias_value":"3MCRF47C3UVPNDON","created_at":"2026-07-05T11:43:57Z"},{"alias_kind":"pith_short_8","alias_value":"3MCRF47C","created_at":"2026-07-05T11:43:57Z"}],"graph_snapshots":[{"event_id":"sha256:8bada89ff308706e8fc1b1dc2782068ab5aaa85f0f39d10c6b71c8ea7a053655","target":"graph","created_at":"2026-07-05T11:43:57Z","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/2410.11824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T17:50:37Z","title":"KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11824","kind":"arxiv","version":2},"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":"sha256:4b641ba47312cc3b1b577c9d690cd1bec397e62b24dfb4658bc4a5731369f0d2","target":"record","created_at":"2026-07-05T11:43:57Z","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":"6cb64405def9cb2d38d6aba926b9550f4eecea15d3b4fc1cf56a26276ce50288","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T17:50:37Z","title_canon_sha256":"57a3205f3a6b5ca369792fb09ed101ed927e99985bb32a75df66888b98eade3e"},"schema_version":"1.0","source":{"id":"2410.11824","kind":"arxiv","version":2}},"canonical_sha256":"db0512f3e2dd2af68dcdb408b0318f8969a0f077da113b45d74e5343f4e904fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db0512f3e2dd2af68dcdb408b0318f8969a0f077da113b45d74e5343f4e904fb","first_computed_at":"2026-07-05T11:43:57.785817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:57.785817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v0I++tTtsjdquLUHTOy0RZDXOaL85rkATxpHhRYJkQ4i3moLmKR63Z/Hhsp33L0qmTLDKdIix9r4KuAyk3+XCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:57.786343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11824","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b641ba47312cc3b1b577c9d690cd1bec397e62b24dfb4658bc4a5731369f0d2","sha256:8bada89ff308706e8fc1b1dc2782068ab5aaa85f0f39d10c6b71c8ea7a053655"],"state_sha256":"eccbf852038a6258855b7b52a563dc2fddc4d89f36d8b27b4224ac054547902d"}