{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G43GURTGGYMMWWEAA7ME2PO6FX","short_pith_number":"pith:G43GURTG","schema_version":"1.0","canonical_sha256":"37366a46663618cb588007d84d3dde2dfe617485b8894e43745dd5354f3ee22e","source":{"kind":"arxiv","id":"2505.24787","version":1},"attestation_state":"computed","paper":{"title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiahao Yuan, Qianning Wang, Yucheng Zhou","submitted_at":"2025-05-30T16:48:14Z","abstract_excerpt":"Recent advancements in text-to-image (T2I) generation have enabled models to produce high-quality images from textual descriptions. However, these models often struggle with complex instructions involving multiple objects, attributes, and spatial relationships. Existing benchmarks for evaluating T2I models primarily focus on general text-image alignment and fail to capture the nuanced requirements of complex, multi-faceted prompts. Given this gap, we introduce LongBench-T2I, a comprehensive benchmark specifically designed to evaluate T2I models under complex instructions. LongBench-T2I consist"},"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":"2505.24787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T16:48:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b11cd8cf65a74319e0e13801a91312619c7240df175911e94409dc4d4242f0c7","abstract_canon_sha256":"8f27a2ff5934c4d90e6f70b1685bfe0bc19e8a56bc2389c403379b575ca57994"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:56.676349Z","signature_b64":"1YzgjqwqDnM4u6iYdFFDRINpMxHaikPkOowSWXstXzTfcIxGmcY2ahGOJ6ab0Wi7WthnRLcWwL7MrNuBrO8nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37366a46663618cb588007d84d3dde2dfe617485b8894e43745dd5354f3ee22e","last_reissued_at":"2026-07-05T11:12:56.675776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:56.675776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiahao Yuan, Qianning Wang, Yucheng Zhou","submitted_at":"2025-05-30T16:48:14Z","abstract_excerpt":"Recent advancements in text-to-image (T2I) generation have enabled models to produce high-quality images from textual descriptions. However, these models often struggle with complex instructions involving multiple objects, attributes, and spatial relationships. Existing benchmarks for evaluating T2I models primarily focus on general text-image alignment and fail to capture the nuanced requirements of complex, multi-faceted prompts. Given this gap, we introduce LongBench-T2I, a comprehensive benchmark specifically designed to evaluate T2I models under complex instructions. LongBench-T2I consist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24787","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/2505.24787/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":"2505.24787","created_at":"2026-07-05T11:12:56.675841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24787v1","created_at":"2026-07-05T11:12:56.675841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24787","created_at":"2026-07-05T11:12:56.675841+00:00"},{"alias_kind":"pith_short_12","alias_value":"G43GURTGGYMM","created_at":"2026-07-05T11:12:56.675841+00:00"},{"alias_kind":"pith_short_16","alias_value":"G43GURTGGYMMWWEA","created_at":"2026-07-05T11:12:56.675841+00:00"},{"alias_kind":"pith_short_8","alias_value":"G43GURTG","created_at":"2026-07-05T11:12:56.675841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02355","citing_title":"From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14166","citing_title":"Hierarchical Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19857","citing_title":"Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX","json":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX.json","graph_json":"https://pith.science/api/pith-number/G43GURTGGYMMWWEAA7ME2PO6FX/graph.json","events_json":"https://pith.science/api/pith-number/G43GURTGGYMMWWEAA7ME2PO6FX/events.json","paper":"https://pith.science/paper/G43GURTG"},"agent_actions":{"view_html":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX","download_json":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX.json","view_paper":"https://pith.science/paper/G43GURTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24787&json=true","fetch_graph":"https://pith.science/api/pith-number/G43GURTGGYMMWWEAA7ME2PO6FX/graph.json","fetch_events":"https://pith.science/api/pith-number/G43GURTGGYMMWWEAA7ME2PO6FX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX/action/storage_attestation","attest_author":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX/action/author_attestation","sign_citation":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX/action/citation_signature","submit_replication":"https://pith.science/pith/G43GURTGGYMMWWEAA7ME2PO6FX/action/replication_record"}},"created_at":"2026-07-05T11:12:56.675841+00:00","updated_at":"2026-07-05T11:12:56.675841+00:00"}