{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HJV7T4D47LD5HIYO2SL65YT33X","short_pith_number":"pith:HJV7T4D4","schema_version":"1.0","canonical_sha256":"3a6bf9f07cfac7d3a30ed497eee27bddc43b0a5899df4b6ba02b57c74e1637d4","source":{"kind":"arxiv","id":"2501.13920","version":1},"attestation_state":"computed","paper":{"title":"IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jiayi Lei, Le Zhuo, Peng Gao, Renrui Zhang, Ruoyi Du, Shitian Zhao, Weifeng Lin, Wenjian Sun, Xiangfei Hu, Xinyue Li, Yiting Lu, Zhen Li, Zhongyu Li, Ziyu Guo","submitted_at":"2025-01-23T18:58:33Z","abstract_excerpt":"With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0, along with others like Dall-E3 and Stable Diffusion 3, have demonstrated exceptional performance across various complex tasks, raising questions about whether T2I models are moving towards general-purpose applicability. Beyond traditional image generation, these models exhibit capabilities across a range of fields, including controllable generation, image editi"},"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":"2501.13920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:58:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"75bc3fd9d4cafee64b9e5c674af2cf92b83ae8152324e5b49e681aebe945627f","abstract_canon_sha256":"b4b00f880dac27f85a63cddbe42c9067af1a2920f47210c956ed0bb5f727901a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:35.989630Z","signature_b64":"sFjE4fON5oA3lB5kbZZjH0fZJUz8NplTEA0WoGHyz+0vLGqb18izsfmZkzTQAImCiU/QfPPk6cmIYo3bwtDCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a6bf9f07cfac7d3a30ed497eee27bddc43b0a5899df4b6ba02b57c74e1637d4","last_reissued_at":"2026-07-05T10:04:35.989247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:35.989247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jiayi Lei, Le Zhuo, Peng Gao, Renrui Zhang, Ruoyi Du, Shitian Zhao, Weifeng Lin, Wenjian Sun, Xiangfei Hu, Xinyue Li, Yiting Lu, Zhen Li, Zhongyu Li, Ziyu Guo","submitted_at":"2025-01-23T18:58:33Z","abstract_excerpt":"With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0, along with others like Dall-E3 and Stable Diffusion 3, have demonstrated exceptional performance across various complex tasks, raising questions about whether T2I models are moving towards general-purpose applicability. Beyond traditional image generation, these models exhibit capabilities across a range of fields, including controllable generation, image editi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13920","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/2501.13920/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":"2501.13920","created_at":"2026-07-05T10:04:35.989312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13920v1","created_at":"2026-07-05T10:04:35.989312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13920","created_at":"2026-07-05T10:04:35.989312+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJV7T4D47LD5","created_at":"2026-07-05T10:04:35.989312+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJV7T4D47LD5HIYO","created_at":"2026-07-05T10:04:35.989312+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJV7T4D4","created_at":"2026-07-05T10:04:35.989312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23493","citing_title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X","json":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X.json","graph_json":"https://pith.science/api/pith-number/HJV7T4D47LD5HIYO2SL65YT33X/graph.json","events_json":"https://pith.science/api/pith-number/HJV7T4D47LD5HIYO2SL65YT33X/events.json","paper":"https://pith.science/paper/HJV7T4D4"},"agent_actions":{"view_html":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X","download_json":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X.json","view_paper":"https://pith.science/paper/HJV7T4D4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13920&json=true","fetch_graph":"https://pith.science/api/pith-number/HJV7T4D47LD5HIYO2SL65YT33X/graph.json","fetch_events":"https://pith.science/api/pith-number/HJV7T4D47LD5HIYO2SL65YT33X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X/action/storage_attestation","attest_author":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X/action/author_attestation","sign_citation":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X/action/citation_signature","submit_replication":"https://pith.science/pith/HJV7T4D47LD5HIYO2SL65YT33X/action/replication_record"}},"created_at":"2026-07-05T10:04:35.989312+00:00","updated_at":"2026-07-05T10:04:35.989312+00:00"}