{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7BFEBOB5HXO2BGPW7G3TVIZAHN","short_pith_number":"pith:7BFEBOB5","schema_version":"1.0","canonical_sha256":"f84a40b83d3ddda099f6f9b73aa3203b45b39d4ce4f0f9ffa151706f8b1f973f","source":{"kind":"arxiv","id":"2605.13141","version":1},"attestation_state":"computed","paper":{"title":"UIBenchKit: A unified toolkit for design-to-code model evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chinh T. Le, Jingyu Xiao, Trevor Ong Yee Siang, Yintong Huo, Yuxuan Wan","submitted_at":"2026-05-13T08:06:41Z","abstract_excerpt":"Recent years have seen substantial progress in automated design-to-code generation, with many methods proposed for generating HTML and CSS from webpage screenshots. However, the absence of a standardized evaluation platform makes it difficult to compare these methods fairly, limiting both practical adoption and systematic research progress. To bridge this gap, we introduce UIBenchKit, an open-source, integrated toolkit designed to unify the evaluation of design-to-code tasks. UIBenchKit abstracts the complexities of environment setup, model inference, and code rendering, offering researchers a"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T08:06:41Z","cross_cats_sorted":[],"title_canon_sha256":"82aea0cc87d28397207494098ae9bd408dfb41c10dc798027f5ce2682742b9da","abstract_canon_sha256":"2bc4c368c44edd0bca00dc644115e3039244a50a0eb799e0161c7a27857cb5ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:57.416059Z","signature_b64":"B9IK9Fmllm43NVNEfwHiRaGvWkLYp/WBA9RBgFxo+3/Z0bi6o/4gq4aqHHHO9KqZH2FCAnV+YgjyGKc3e3NqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f84a40b83d3ddda099f6f9b73aa3203b45b39d4ce4f0f9ffa151706f8b1f973f","last_reissued_at":"2026-05-18T03:08:57.415111Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:57.415111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UIBenchKit: A unified toolkit for design-to-code model evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chinh T. Le, Jingyu Xiao, Trevor Ong Yee Siang, Yintong Huo, Yuxuan Wan","submitted_at":"2026-05-13T08:06:41Z","abstract_excerpt":"Recent years have seen substantial progress in automated design-to-code generation, with many methods proposed for generating HTML and CSS from webpage screenshots. However, the absence of a standardized evaluation platform makes it difficult to compare these methods fairly, limiting both practical adoption and systematic research progress. To bridge this gap, we introduce UIBenchKit, an open-source, integrated toolkit designed to unify the evaluation of design-to-code tasks. UIBenchKit abstracts the complexities of environment setup, model inference, and code rendering, offering researchers a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"UIBenchKit abstracts the complexities of environment setup, model inference, and code rendering, offering researchers a plug-and-play architecture to compare various methods under consistent settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen metrics and analytical interface meaningfully capture real-world quality differences between generated code outputs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UIBenchKit is a unified open-source toolkit providing plug-and-play evaluation for design-to-code generation models with consistent settings and multi-metric analysis.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f2c38f8c27f5227a46c99565098798848b09c2cdc988c439f7bee91c00d49f45"},"source":{"id":"2605.13141","kind":"arxiv","version":1},"verdict":{"id":"13e9ded0-04ad-4a96-a4cd-59d3a1c6de4b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:28:47.447131Z","strongest_claim":"UIBenchKit abstracts the complexities of environment setup, model inference, and code rendering, offering researchers a plug-and-play architecture to compare various methods under consistent settings.","one_line_summary":"UIBenchKit is a unified open-source toolkit providing plug-and-play evaluation for design-to-code generation models with consistent settings and multi-metric analysis.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen metrics and analytical interface meaningfully capture real-world quality differences between generated code outputs.","pith_extraction_headline":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions."},"references":{"count":14,"sample":[{"doi":"","year":2026,"title":"Max Bachmann. 2026. Levenshtein Distance — RapidFuzz Documentation. https: //rapidfuzz.github.io/Levenshtein/levenshtein.html Accessed: 2026-02-26","work_id":"bef538b6-3e6c-4ab5-9ec8-226681baf1aa","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Yi Gui, Zhen Li, Zhongyi Zhang, Yao Wan, Dongping Chen, Hongyu Zhang, Yi Su, Bohua Chen, Xing Zhou, Wenbin Jiang, and Xiangliang Zhang. 2025. UICopilot: Automating UI Synthesis via Hierarchical Code G","work_id":"8996b873-4dd9-43bc-9894-f21b647ecd45","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Yi Gui, Zhen Li, Zhongyi Zhang, Guohao Wang, Tianpeng Lv, Gaoyang Jiang, Yi Liu, Dongping Chen, Yao Wan, Hongyu Zhang, Wenbin Jiang, Xuanhua Shi, and Hai Jin. 2025. <scp>LaTCoder:</scp> Converting Web","work_id":"939f4b56-1ee3-44a2-967e-a103ac64fa69","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Jason Lemkin. 2025. How Vercel Hit $9.3B and Replit Hit $3B. . . After a Decade: The Long Paths to AI Overnight Success. https://www.saastr.com/how-vercel- hit-9-3b-and-replit-hit-3b-after-a-decade-th","work_id":"7710b266-f134-4b43-81c4-8af7878cc48d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Meta Open Source. [n. d.]. React Documentation. https://react.dev/. Accessed: 2026-05-10","work_id":"9c35f327-9460-47e4-a364-eb8f3c1d70f5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":14,"snapshot_sha256":"533df2bedf79c760985f155f57974adfe1110cfea5c367607d70d37d601fd560","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":"2605.13141","created_at":"2026-05-18T03:08:57.415261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13141v1","created_at":"2026-05-18T03:08:57.415261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13141","created_at":"2026-05-18T03:08:57.415261+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BFEBOB5HXO2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BFEBOB5HXO2BGPW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BFEBOB5","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN","json":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN.json","graph_json":"https://pith.science/api/pith-number/7BFEBOB5HXO2BGPW7G3TVIZAHN/graph.json","events_json":"https://pith.science/api/pith-number/7BFEBOB5HXO2BGPW7G3TVIZAHN/events.json","paper":"https://pith.science/paper/7BFEBOB5"},"agent_actions":{"view_html":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN","download_json":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN.json","view_paper":"https://pith.science/paper/7BFEBOB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13141&json=true","fetch_graph":"https://pith.science/api/pith-number/7BFEBOB5HXO2BGPW7G3TVIZAHN/graph.json","fetch_events":"https://pith.science/api/pith-number/7BFEBOB5HXO2BGPW7G3TVIZAHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN/action/storage_attestation","attest_author":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN/action/author_attestation","sign_citation":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN/action/citation_signature","submit_replication":"https://pith.science/pith/7BFEBOB5HXO2BGPW7G3TVIZAHN/action/replication_record"}},"created_at":"2026-05-18T03:08:57.415261+00:00","updated_at":"2026-05-18T03:08:57.415261+00:00"}