{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3MCRF47C3UVPNDONWQELAMMPRF","short_pith_number":"pith:3MCRF47C","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"},"canonical_sha256":"db0512f3e2dd2af68dcdb408b0318f8969a0f077da113b45d74e5343f4e904fb","source":{"kind":"arxiv","id":"2410.11824","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3MCRF47C3UVPNDONWQELAMMPRF","target":"record","payload":{"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"},"canonical_sha256":"db0512f3e2dd2af68dcdb408b0318f8969a0f077da113b45d74e5343f4e904fb","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"},"source_kind":"arxiv","source_id":"2410.11824","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zi8Zb2bgP4/9kbEAz6jM6qffly6ff6ihTn68ZrkWE0F40EVs4Z1UGbkL8QMgUv2mRruPD34m9kyyuSL7sEt0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:08.788674Z"},"content_sha256":"4b641ba47312cc3b1b577c9d690cd1bec397e62b24dfb4658bc4a5731369f0d2","schema_version":"1.0","event_id":"sha256:4b641ba47312cc3b1b577c9d690cd1bec397e62b24dfb4658bc4a5731369f0d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3MCRF47C3UVPNDONWQELAMMPRF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZp/wkS5JtdTnHS6qGPcPlPFFBX01c2XZhVqrn6F1/VsxlXsZnADVPw6NG63t4pubbuhUBGgsEoiMBomEeXnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:08.789043Z"},"content_sha256":"8bada89ff308706e8fc1b1dc2782068ab5aaa85f0f39d10c6b71c8ea7a053655","schema_version":"1.0","event_id":"sha256:8bada89ff308706e8fc1b1dc2782068ab5aaa85f0f39d10c6b71c8ea7a053655"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/bundle.json","state_url":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MCRF47C3UVPNDONWQELAMMPRF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:32:08Z","links":{"resolver":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF","bundle":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/bundle.json","state":"https://pith.science/pith/3MCRF47C3UVPNDONWQELAMMPRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MCRF47C3UVPNDONWQELAMMPRF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D56NSxpMp9aHXbWm+4vZ+loC0emMVb7YFbwfzX9LO30fmrAO849jSgJRFgHckdMHeI2SRhCY8o6VV+XKBlwTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:32:08.791048Z","bundle_sha256":"c91aeb228b9ae53e97283b66dd4eebba951e6c5bb9fcf6da888bd06a0dba71cf"}}