{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TSJHFKADYEHPCHCUL7NT6I62OR","short_pith_number":"pith:TSJHFKAD","canonical_record":{"source":{"id":"2503.07265","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T12:47:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a44df9da20e1ddbd7d7d568e7762a43b8193cc99caafb92e23778ca9050dfcb9","abstract_canon_sha256":"bf709dab7ee32b19d092e1a7de86f67f5ce30b8b494b9bf09f2aed3e12bc94aa"},"schema_version":"1.0"},"canonical_sha256":"9c9272a803c10ef11c545fdb3f23da74652492389699e99f44a7b54efd11347d","source":{"kind":"arxiv","id":"2503.07265","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07265","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07265v3","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07265","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"TSJHFKADYEHP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TSJHFKADYEHPCHCU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TSJHFKAD","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TSJHFKADYEHPCHCUL7NT6I62OR","target":"record","payload":{"canonical_record":{"source":{"id":"2503.07265","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T12:47:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a44df9da20e1ddbd7d7d568e7762a43b8193cc99caafb92e23778ca9050dfcb9","abstract_canon_sha256":"bf709dab7ee32b19d092e1a7de86f67f5ce30b8b494b9bf09f2aed3e12bc94aa"},"schema_version":"1.0"},"canonical_sha256":"9c9272a803c10ef11c545fdb3f23da74652492389699e99f44a7b54efd11347d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.927171Z","signature_b64":"YvJuP/r4b6J3xC9R7wFI+Q6C6eJh/RqwDLtRv5S7isE6+9fte4/j6Ct1yfDEHNO4ptADEyV5apBHQK9aIts1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c9272a803c10ef11c545fdb3f23da74652492389699e99f44a7b54efd11347d","last_reissued_at":"2026-05-17T23:38:50.926726Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.926726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.07265","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j387OAMoxa/GATaIybejIju2+9srHAw913n51GqNqKb6oqH7aWcrIgrkf0wyrxwNOEdSkjc7DPivQ5x5Oo4gBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:12:25.213560Z"},"content_sha256":"912f2f1e8f5e8c349bd44f3db5a1b270d36258dc1588876fe47c09bd65c0fb72","schema_version":"1.0","event_id":"sha256:912f2f1e8f5e8c349bd44f3db5a1b270d36258dc1588876fe47c09bd65c0fb72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TSJHFKADYEHPCHCUL7NT6I62OR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Text-to-image models struggle to apply world knowledge in generated images according to a dedicated new benchmark.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Lin, Bin Zhu, Chaoran Feng, Jiaqi Liao, Kunpeng Ning, Li Yuan, Mengren Zheng, Munan Ning, Peng Jin, Weiyang Jin, Yuwei Niu","submitted_at":"2025-03-10T12:47:53Z","abstract_excerpt":"Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evaluation standards predominantly focus on image realism and shallow text-image alignment, lacking a comprehensive assessment of complex semantic understanding and world knowledge integration in text-to-image generation. To address this challenge, we propose \\textbf{WISE}, the first benchmark specifically designed for \\textbf{W}orld Knowledge-\\textbf{I}nformed \\textbf{S}emantic \\textbf{E}valuation. WISE moves beyond simple word-pixel mapping by challenging mo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our findings reveal significant limitations in their ability to effectively integrate and apply world knowledge during image generation, highlighting critical pathways for enhancing knowledge incorporation and application in next-generation T2I models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 1000 crafted prompts and 25 subdomains provide unbiased, comprehensive tests of world knowledge integration without post-hoc selection effects or prompt engineering artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Text-to-image models struggle to apply world knowledge in generated images according to a dedicated new benchmark.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"edadc41a735de8c196995cd2dcdcbd3ff83b849ba526f3985ac59fcc8c849790"},"source":{"id":"2503.07265","kind":"arxiv","version":3},"verdict":{"id":"1adc6059-3f59-4f90-9467-c82a0595476a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T16:18:34.201092Z","strongest_claim":"our findings reveal significant limitations in their ability to effectively integrate and apply world knowledge during image generation, highlighting critical pathways for enhancing knowledge incorporation and application in next-generation T2I models.","one_line_summary":"Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 1000 crafted prompts and 25 subdomains provide unbiased, comprehensive tests of world knowledge integration without post-hoc selection effects or prompt engineering artifacts.","pith_extraction_headline":"Text-to-image models struggle to apply world knowledge in generated images according to a dedicated new benchmark."},"references":{"count":61,"sample":[{"doi":"","year":2023,"title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthe- sis, 2023","work_id":"6917650a-4a8f-4f92-88f8-efd7cd5388a6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","work_id":"86d896d2-592f-4d9b-938e-dfeb11f9388f","ref_index":2,"cited_arxiv_id":"2505.09568","is_internal_anchor":true},{"doi":"","year":2024,"title":"Next token prediction towards multimodal intelligence: A comprehensive survey","work_id":"5cdd7b0b-6c98-4848-901b-eab0a5c3f9e6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Generative pretraining from pixels","work_id":"0747dcb4-e395-4187-9b0b-dadb91e6cb2b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","work_id":"67d9e391-26d1-459e-ab56-07e60511c886","ref_index":5,"cited_arxiv_id":"2501.17811","is_internal_anchor":true}],"resolved_work":61,"snapshot_sha256":"577510af768e568d8e73cc1b69bd6894d00aa54f407977ae229de95ebe08860b","internal_anchors":23},"formal_canon":{"evidence_count":2,"snapshot_sha256":"94fb97ae272139d7986f88dd4fddf08517d5c0f8c287e222f9e2431bfb1bf164"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1adc6059-3f59-4f90-9467-c82a0595476a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HXaepCNceOsNfdn5qMPnnpzJEvP3/e8kstV4ZwwoM92bWfML94m7tQqBnAwRd2Mj4CR+oQt3vTnDEb9SiVkqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:12:25.214096Z"},"content_sha256":"7b3f155edbd09d31387fa5b7f97169ecc80ca7248aadaa63e17d0708b87bebb0","schema_version":"1.0","event_id":"sha256:7b3f155edbd09d31387fa5b7f97169ecc80ca7248aadaa63e17d0708b87bebb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSJHFKADYEHPCHCUL7NT6I62OR/bundle.json","state_url":"https://pith.science/pith/TSJHFKADYEHPCHCUL7NT6I62OR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSJHFKADYEHPCHCUL7NT6I62OR/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":"2026-06-01T19:12:25Z","links":{"resolver":"https://pith.science/pith/TSJHFKADYEHPCHCUL7NT6I62OR","bundle":"https://pith.science/pith/TSJHFKADYEHPCHCUL7NT6I62OR/bundle.json","state":"https://pith.science/pith/TSJHFKADYEHPCHCUL7NT6I62OR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSJHFKADYEHPCHCUL7NT6I62OR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TSJHFKADYEHPCHCUL7NT6I62OR","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":"bf709dab7ee32b19d092e1a7de86f67f5ce30b8b494b9bf09f2aed3e12bc94aa","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T12:47:53Z","title_canon_sha256":"a44df9da20e1ddbd7d7d568e7762a43b8193cc99caafb92e23778ca9050dfcb9"},"schema_version":"1.0","source":{"id":"2503.07265","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07265","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07265v3","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07265","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"TSJHFKADYEHP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TSJHFKADYEHPCHCU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TSJHFKAD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7b3f155edbd09d31387fa5b7f97169ecc80ca7248aadaa63e17d0708b87bebb0","target":"graph","created_at":"2026-05-17T23:38:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"our findings reveal significant limitations in their ability to effectively integrate and apply world knowledge during image generation, highlighting critical pathways for enhancing knowledge incorporation and application in next-generation T2I models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 1000 crafted prompts and 25 subdomains provide unbiased, comprehensive tests of world knowledge integration without post-hoc selection effects or prompt engineering artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Text-to-image models struggle to apply world knowledge in generated images according to a dedicated new benchmark."}],"snapshot_sha256":"edadc41a735de8c196995cd2dcdcbd3ff83b849ba526f3985ac59fcc8c849790"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"94fb97ae272139d7986f88dd4fddf08517d5c0f8c287e222f9e2431bfb1bf164"},"paper":{"abstract_excerpt":"Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evaluation standards predominantly focus on image realism and shallow text-image alignment, lacking a comprehensive assessment of complex semantic understanding and world knowledge integration in text-to-image generation. To address this challenge, we propose \\textbf{WISE}, the first benchmark specifically designed for \\textbf{W}orld Knowledge-\\textbf{I}nformed \\textbf{S}emantic \\textbf{E}valuation. WISE moves beyond simple word-pixel mapping by challenging mo","authors_text":"Bin Lin, Bin Zhu, Chaoran Feng, Jiaqi Liao, Kunpeng Ning, Li Yuan, Mengren Zheng, Munan Ning, Peng Jin, Weiyang Jin, Yuwei Niu","cross_cats":["cs.AI","cs.CL"],"headline":"Text-to-image models struggle to apply world knowledge in generated images according to a dedicated new benchmark.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T12:47:53Z","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation"},"references":{"count":61,"internal_anchors":23,"resolved_work":61,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthe- sis, 2023","work_id":"6917650a-4a8f-4f92-88f8-efd7cd5388a6","year":2023},{"cited_arxiv_id":"2505.09568","doi":"","is_internal_anchor":true,"ref_index":2,"title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","work_id":"86d896d2-592f-4d9b-938e-dfeb11f9388f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Next token prediction towards multimodal intelligence: A comprehensive survey","work_id":"5cdd7b0b-6c98-4848-901b-eab0a5c3f9e6","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Generative pretraining from pixels","work_id":"0747dcb4-e395-4187-9b0b-dadb91e6cb2b","year":2020},{"cited_arxiv_id":"2501.17811","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","work_id":"67d9e391-26d1-459e-ab56-07e60511c886","year":2025}],"snapshot_sha256":"577510af768e568d8e73cc1b69bd6894d00aa54f407977ae229de95ebe08860b"},"source":{"id":"2503.07265","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T16:18:34.201092Z","id":"1adc6059-3f59-4f90-9467-c82a0595476a","model_set":{"reader":"grok-4.3"},"one_line_summary":"Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Text-to-image models struggle to apply world knowledge in generated images according to a dedicated new benchmark.","strongest_claim":"our findings reveal significant limitations in their ability to effectively integrate and apply world knowledge during image generation, highlighting critical pathways for enhancing knowledge incorporation and application in next-generation T2I models.","weakest_assumption":"That the 1000 crafted prompts and 25 subdomains provide unbiased, comprehensive tests of world knowledge integration without post-hoc selection effects or prompt engineering artifacts."}},"verdict_id":"1adc6059-3f59-4f90-9467-c82a0595476a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:912f2f1e8f5e8c349bd44f3db5a1b270d36258dc1588876fe47c09bd65c0fb72","target":"record","created_at":"2026-05-17T23:38:50Z","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":"bf709dab7ee32b19d092e1a7de86f67f5ce30b8b494b9bf09f2aed3e12bc94aa","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T12:47:53Z","title_canon_sha256":"a44df9da20e1ddbd7d7d568e7762a43b8193cc99caafb92e23778ca9050dfcb9"},"schema_version":"1.0","source":{"id":"2503.07265","kind":"arxiv","version":3}},"canonical_sha256":"9c9272a803c10ef11c545fdb3f23da74652492389699e99f44a7b54efd11347d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c9272a803c10ef11c545fdb3f23da74652492389699e99f44a7b54efd11347d","first_computed_at":"2026-05-17T23:38:50.926726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.926726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YvJuP/r4b6J3xC9R7wFI+Q6C6eJh/RqwDLtRv5S7isE6+9fte4/j6Ct1yfDEHNO4ptADEyV5apBHQK9aIts1CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.927171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07265","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:912f2f1e8f5e8c349bd44f3db5a1b270d36258dc1588876fe47c09bd65c0fb72","sha256:7b3f155edbd09d31387fa5b7f97169ecc80ca7248aadaa63e17d0708b87bebb0"],"state_sha256":"a4c7cdfe805669b4b2d54747ef55b61fe0d5e34a34a85b19cb764bdc60e377b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"baPKa1x38UhiDKmZqTyrWById1yhzqHKaU5QoVqPaVbMZg4ZjcNSZDgIurHqbIQLW2neFF8KyWmlvVycXHSIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T19:12:25.216544Z","bundle_sha256":"263ba2500b2b41d955ebff4d89f418952d8128d7edbcef70ff2163dd970da605"}}