{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AG37PQOM2IJCX3EKHJHKDVLSRR","short_pith_number":"pith:AG37PQOM","schema_version":"1.0","canonical_sha256":"01b7f7c1ccd2122bec8a3a4ea1d5728c514b5a3365df65c5bff8626b25268916","source":{"kind":"arxiv","id":"2505.18730","version":1},"attestation_state":"computed","paper":{"title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahe Tian, Jiao Dai, Jizhong Han, Miaomiao Feng, Runze He, Wei Mi, Wenchao Zhang, Xiaodan Zhang","submitted_at":"2025-05-24T14:56:09Z","abstract_excerpt":"Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmarks primarily focus on the explicit alignment between generated images and prompts, neglecting the alignment with real-world knowledge beyond prompts. To address this gap, we introduce Align Beyond Prompts (ABP), a comprehensive benchmark designed to measure the alignment of generated images with real-world knowledge that extends beyond the explicit user prompts. ABP comprises over 2,000 meticulously crafted prompts, c"},"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":"2505.18730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T14:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"2b49489df099b1a102315affcd968d99d454337217814d59dd33ec9a084405c6","abstract_canon_sha256":"af019fdc570608b4845c8dd82486e9b0ebaa3b37da5e2d16d34363be96fdb7cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:18.674923Z","signature_b64":"7kautG/MWRxzZxBB4VMZU+sd9G09ZZVEkwyXx6L2OwOW+NuZBhfJ5k9fxbspEEwPMP8555yBizc2fWlBjtbdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01b7f7c1ccd2122bec8a3a4ea1d5728c514b5a3365df65c5bff8626b25268916","last_reissued_at":"2026-07-05T11:09:18.674524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:18.674524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahe Tian, Jiao Dai, Jizhong Han, Miaomiao Feng, Runze He, Wei Mi, Wenchao Zhang, Xiaodan Zhang","submitted_at":"2025-05-24T14:56:09Z","abstract_excerpt":"Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmarks primarily focus on the explicit alignment between generated images and prompts, neglecting the alignment with real-world knowledge beyond prompts. To address this gap, we introduce Align Beyond Prompts (ABP), a comprehensive benchmark designed to measure the alignment of generated images with real-world knowledge that extends beyond the explicit user prompts. ABP comprises over 2,000 meticulously crafted prompts, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18730","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/2505.18730/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":"2505.18730","created_at":"2026-07-05T11:09:18.674580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18730v1","created_at":"2026-07-05T11:09:18.674580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18730","created_at":"2026-07-05T11:09:18.674580+00:00"},{"alias_kind":"pith_short_12","alias_value":"AG37PQOM2IJC","created_at":"2026-07-05T11:09:18.674580+00:00"},{"alias_kind":"pith_short_16","alias_value":"AG37PQOM2IJCX3EK","created_at":"2026-07-05T11:09:18.674580+00:00"},{"alias_kind":"pith_short_8","alias_value":"AG37PQOM","created_at":"2026-07-05T11:09:18.674580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04436","citing_title":"ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR","json":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR.json","graph_json":"https://pith.science/api/pith-number/AG37PQOM2IJCX3EKHJHKDVLSRR/graph.json","events_json":"https://pith.science/api/pith-number/AG37PQOM2IJCX3EKHJHKDVLSRR/events.json","paper":"https://pith.science/paper/AG37PQOM"},"agent_actions":{"view_html":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR","download_json":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR.json","view_paper":"https://pith.science/paper/AG37PQOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18730&json=true","fetch_graph":"https://pith.science/api/pith-number/AG37PQOM2IJCX3EKHJHKDVLSRR/graph.json","fetch_events":"https://pith.science/api/pith-number/AG37PQOM2IJCX3EKHJHKDVLSRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR/action/storage_attestation","attest_author":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR/action/author_attestation","sign_citation":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR/action/citation_signature","submit_replication":"https://pith.science/pith/AG37PQOM2IJCX3EKHJHKDVLSRR/action/replication_record"}},"created_at":"2026-07-05T11:09:18.674580+00:00","updated_at":"2026-07-05T11:09:18.674580+00:00"}