{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JWUSFMO7KNHPTXWA7F3S4GHHQH","short_pith_number":"pith:JWUSFMO7","schema_version":"1.0","canonical_sha256":"4da922b1df534ef9dec0f9772e18e781caa87e47b769c4ccc77a3b0c37bd0554","source":{"kind":"arxiv","id":"2310.08541","version":2},"attestation_state":"computed","paper":{"title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-10-12T17:34:20Z","abstract_excerpt":"We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models via iterative explorations. This enables them to efficiently convert their high-level generation ideas into effective T2I prompts that can produce good images. We investigate if systems based on large multimodal models (LMMs) can develop analogous multimodal self-refinement abilities that enable exploring unknown models or environments via self-refining tri"},"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":"2310.08541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:34:20Z","cross_cats_sorted":[],"title_canon_sha256":"76642aa34dc881d442a5a0eaffc9f2f016717877a16ca6b38afdfc174b38915d","abstract_canon_sha256":"83a9542ae40bf2a263d87213304271aa6f6ce99f31a7945c17bda4bdb47fa971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:20.804961Z","signature_b64":"qpgyBI72/XzR3P9M+u43EXHgMwU3/mKYPc3HuuT7czXjzlA9aaYEITtbJmbGYTWCLs0BNllBghZ5lodbCO0WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4da922b1df534ef9dec0f9772e18e781caa87e47b769c4ccc77a3b0c37bd0554","last_reissued_at":"2026-07-05T08:55:20.804563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:20.804563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-10-12T17:34:20Z","abstract_excerpt":"We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models via iterative explorations. This enables them to efficiently convert their high-level generation ideas into effective T2I prompts that can produce good images. We investigate if systems based on large multimodal models (LMMs) can develop analogous multimodal self-refinement abilities that enable exploring unknown models or environments via self-refining tri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08541","kind":"arxiv","version":2},"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/2310.08541/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":"2310.08541","created_at":"2026-07-05T08:55:20.804630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08541v2","created_at":"2026-07-05T08:55:20.804630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08541","created_at":"2026-07-05T08:55:20.804630+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWUSFMO7KNHP","created_at":"2026-07-05T08:55:20.804630+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWUSFMO7KNHPTXWA","created_at":"2026-07-05T08:55:20.804630+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWUSFMO7","created_at":"2026-07-05T08:55:20.804630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01803","citing_title":"OctoT2I: A Self-Evolving Agentic Text-to-Image Router","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH","json":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH.json","graph_json":"https://pith.science/api/pith-number/JWUSFMO7KNHPTXWA7F3S4GHHQH/graph.json","events_json":"https://pith.science/api/pith-number/JWUSFMO7KNHPTXWA7F3S4GHHQH/events.json","paper":"https://pith.science/paper/JWUSFMO7"},"agent_actions":{"view_html":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH","download_json":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH.json","view_paper":"https://pith.science/paper/JWUSFMO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08541&json=true","fetch_graph":"https://pith.science/api/pith-number/JWUSFMO7KNHPTXWA7F3S4GHHQH/graph.json","fetch_events":"https://pith.science/api/pith-number/JWUSFMO7KNHPTXWA7F3S4GHHQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH/action/storage_attestation","attest_author":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH/action/author_attestation","sign_citation":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH/action/citation_signature","submit_replication":"https://pith.science/pith/JWUSFMO7KNHPTXWA7F3S4GHHQH/action/replication_record"}},"created_at":"2026-07-05T08:55:20.804630+00:00","updated_at":"2026-07-05T08:55:20.804630+00:00"}