{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZW6XBW56KKF3KOX3PXJS65BAQP","short_pith_number":"pith:ZW6XBW56","schema_version":"1.0","canonical_sha256":"cdbd70dbbe528bb53afb7dd32f742083d7434640c5fd58d0fa04788ea75fb942","source":{"kind":"arxiv","id":"2403.03163","version":3},"attestation_state":"computed","paper":{"title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.CY"],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Diyi Yang, Ruibo Liu, Ryan Li, Yanzhe Zhang, Zhengyuan Yang","submitted_at":"2024-03-05T17:56:27Z","abstract_excerpt":"Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development in which multimodal large language models (MLLMs) directly convert visual designs into code implementations. In this work, we construct Design2Code - the first real-world benchmark for this task. Specifically, we manually curate 484 diverse real-world webpages as test cases and develop a set of automatic evaluation metrics to assess how well current multimodal LLMs can generate the code implement"},"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":"2403.03163","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:56:27Z","cross_cats_sorted":["cs.CV","cs.CY"],"title_canon_sha256":"3446cd07885986e5cf29738a46ead75bbb90248c011575dfa24d1e6f34baded5","abstract_canon_sha256":"deaaec150c13fed2aad1ba4f3cbcdcd7bcd9504b970c18d3983127bda0a708b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:17.368994Z","signature_b64":"/QtQiR4VIyUoNTYxPafVQILIUasE+D4mSZK10tYLp4bmVeytOZn4Rq+nkHRkBRSPlCKBjkZpz9GxiaB0GHvbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdbd70dbbe528bb53afb7dd32f742083d7434640c5fd58d0fa04788ea75fb942","last_reissued_at":"2026-07-05T10:11:17.368495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:17.368495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.CY"],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Diyi Yang, Ruibo Liu, Ryan Li, Yanzhe Zhang, Zhengyuan Yang","submitted_at":"2024-03-05T17:56:27Z","abstract_excerpt":"Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development in which multimodal large language models (MLLMs) directly convert visual designs into code implementations. In this work, we construct Design2Code - the first real-world benchmark for this task. Specifically, we manually curate 484 diverse real-world webpages as test cases and develop a set of automatic evaluation metrics to assess how well current multimodal LLMs can generate the code implement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03163","kind":"arxiv","version":3},"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/2403.03163/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":"2403.03163","created_at":"2026-07-05T10:11:17.368546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03163v3","created_at":"2026-07-05T10:11:17.368546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03163","created_at":"2026-07-05T10:11:17.368546+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZW6XBW56KKF3","created_at":"2026-07-05T10:11:17.368546+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZW6XBW56KKF3KOX3","created_at":"2026-07-05T10:11:17.368546+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZW6XBW56","created_at":"2026-07-05T10:11:17.368546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10334","citing_title":"Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01022","citing_title":"ProductWebGen: Benchmarking Multimodal Product Webpage Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26144","citing_title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26807","citing_title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00750","citing_title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17242","citing_title":"From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13141","citing_title":"UIBenchKit: A unified toolkit for design-to-code model evaluation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18394","citing_title":"OpenGame: Open Agentic Coding for Games","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP","json":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP.json","graph_json":"https://pith.science/api/pith-number/ZW6XBW56KKF3KOX3PXJS65BAQP/graph.json","events_json":"https://pith.science/api/pith-number/ZW6XBW56KKF3KOX3PXJS65BAQP/events.json","paper":"https://pith.science/paper/ZW6XBW56"},"agent_actions":{"view_html":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP","download_json":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP.json","view_paper":"https://pith.science/paper/ZW6XBW56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03163&json=true","fetch_graph":"https://pith.science/api/pith-number/ZW6XBW56KKF3KOX3PXJS65BAQP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZW6XBW56KKF3KOX3PXJS65BAQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP/action/storage_attestation","attest_author":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP/action/author_attestation","sign_citation":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP/action/citation_signature","submit_replication":"https://pith.science/pith/ZW6XBW56KKF3KOX3PXJS65BAQP/action/replication_record"}},"created_at":"2026-07-05T10:11:17.368546+00:00","updated_at":"2026-07-05T10:11:17.368546+00:00"}