{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4TYWJA3XH57EDEAOXO3KENPWW6","short_pith_number":"pith:4TYWJA3X","schema_version":"1.0","canonical_sha256":"e4f16483773f7e41900ebbb6a235f6b78873c6c05d0ef81863bffd5adda9afb2","source":{"kind":"arxiv","id":"2505.23493","version":1},"attestation_state":"computed","paper":{"title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiaxin Zhang, Joy Rimchala, Kaijie Chen, Lifu Huang, Ying Shen, Yuguang Yao, Zhiyang Xu, Zihao Lin","submitted_at":"2025-05-29T14:43:46Z","abstract_excerpt":"Reasoning is a fundamental capability often required in real-world text-to-image (T2I) generation, e.g., generating ``a bitten apple that has been left in the air for more than a week`` necessitates understanding temporal decay and commonsense concepts. While recent T2I models have made impressive progress in producing photorealistic images, their reasoning capability remains underdeveloped and insufficiently evaluated. To bridge this gap, we introduce R2I-Bench, a comprehensive benchmark specifically designed to rigorously assess reasoning-driven T2I generation. R2I-Bench comprises meticulous"},"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":"2505.23493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T14:43:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5474edf1499f901be0040c72e98665ae3f7054c9bf09c2b912cf0ae5d05c6055","abstract_canon_sha256":"2caffce0b51943ab75632882c6d14089f67d19c0d0eacfe5f3b9aea5317e9c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:02.930440Z","signature_b64":"9n7PAGwCt95LJgEphCJxUhEi7DTbeaYtw7N9gZqQDtUibYewejvbvk646qvRphivoRnlQRA7TN4xAQFYhky6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f16483773f7e41900ebbb6a235f6b78873c6c05d0ef81863bffd5adda9afb2","last_reissued_at":"2026-07-05T11:12:02.929915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:02.929915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiaxin Zhang, Joy Rimchala, Kaijie Chen, Lifu Huang, Ying Shen, Yuguang Yao, Zhiyang Xu, Zihao Lin","submitted_at":"2025-05-29T14:43:46Z","abstract_excerpt":"Reasoning is a fundamental capability often required in real-world text-to-image (T2I) generation, e.g., generating ``a bitten apple that has been left in the air for more than a week`` necessitates understanding temporal decay and commonsense concepts. While recent T2I models have made impressive progress in producing photorealistic images, their reasoning capability remains underdeveloped and insufficiently evaluated. To bridge this gap, we introduce R2I-Bench, a comprehensive benchmark specifically designed to rigorously assess reasoning-driven T2I generation. R2I-Bench comprises meticulous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23493","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/2505.23493/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":"2505.23493","created_at":"2026-07-05T11:12:02.929975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23493v1","created_at":"2026-07-05T11:12:02.929975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23493","created_at":"2026-07-05T11:12:02.929975+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TYWJA3XH57E","created_at":"2026-07-05T11:12:02.929975+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TYWJA3XH57EDEAO","created_at":"2026-07-05T11:12:02.929975+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TYWJA3X","created_at":"2026-07-05T11:12:02.929975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30124","citing_title":"SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6","json":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6.json","graph_json":"https://pith.science/api/pith-number/4TYWJA3XH57EDEAOXO3KENPWW6/graph.json","events_json":"https://pith.science/api/pith-number/4TYWJA3XH57EDEAOXO3KENPWW6/events.json","paper":"https://pith.science/paper/4TYWJA3X"},"agent_actions":{"view_html":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6","download_json":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6.json","view_paper":"https://pith.science/paper/4TYWJA3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23493&json=true","fetch_graph":"https://pith.science/api/pith-number/4TYWJA3XH57EDEAOXO3KENPWW6/graph.json","fetch_events":"https://pith.science/api/pith-number/4TYWJA3XH57EDEAOXO3KENPWW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6/action/storage_attestation","attest_author":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6/action/author_attestation","sign_citation":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6/action/citation_signature","submit_replication":"https://pith.science/pith/4TYWJA3XH57EDEAOXO3KENPWW6/action/replication_record"}},"created_at":"2026-07-05T11:12:02.929975+00:00","updated_at":"2026-07-05T11:12:02.929975+00:00"}