{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZW6XBW56KKF3KOX3PXJS65BAQP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"deaaec150c13fed2aad1ba4f3cbcdcd7bcd9504b970c18d3983127bda0a708b1","cross_cats_sorted":["cs.CV","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:56:27Z","title_canon_sha256":"3446cd07885986e5cf29738a46ead75bbb90248c011575dfa24d1e6f34baded5"},"schema_version":"1.0","source":{"id":"2403.03163","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03163","created_at":"2026-07-05T10:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03163v3","created_at":"2026-07-05T10:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03163","created_at":"2026-07-05T10:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZW6XBW56KKF3","created_at":"2026-07-05T10:11:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZW6XBW56KKF3KOX3","created_at":"2026-07-05T10:11:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZW6XBW56","created_at":"2026-07-05T10:11:17Z"}],"graph_snapshots":[{"event_id":"sha256:bd40b32677e66b7b13c36bf11688a31940b479c337ecb55eb6e4b898ffdf68a3","target":"graph","created_at":"2026-07-05T10:11:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.03163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenglei Si, Diyi Yang, Ruibo Liu, Ryan Li, Yanzhe Zhang, Zhengyuan Yang","cross_cats":["cs.CV","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:56:27Z","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03163","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3b4717a92c24474f0cefb3c512781e858d34849ed3bd3fefec514a84a9354175","target":"record","created_at":"2026-07-05T10:11:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"deaaec150c13fed2aad1ba4f3cbcdcd7bcd9504b970c18d3983127bda0a708b1","cross_cats_sorted":["cs.CV","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:56:27Z","title_canon_sha256":"3446cd07885986e5cf29738a46ead75bbb90248c011575dfa24d1e6f34baded5"},"schema_version":"1.0","source":{"id":"2403.03163","kind":"arxiv","version":3}},"canonical_sha256":"cdbd70dbbe528bb53afb7dd32f742083d7434640c5fd58d0fa04788ea75fb942","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdbd70dbbe528bb53afb7dd32f742083d7434640c5fd58d0fa04788ea75fb942","first_computed_at":"2026-07-05T10:11:17.368495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:17.368495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/QtQiR4VIyUoNTYxPafVQILIUasE+D4mSZK10tYLp4bmVeytOZn4Rq+nkHRkBRSPlCKBjkZpz9GxiaB0GHvbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:17.368994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03163","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b4717a92c24474f0cefb3c512781e858d34849ed3bd3fefec514a84a9354175","sha256:bd40b32677e66b7b13c36bf11688a31940b479c337ecb55eb6e4b898ffdf68a3"],"state_sha256":"8a7889087e423d198cc5c742930ab4f8f4fa060474f6062dc6a1aa5e97e65406"}