{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7BFEBOB5HXO2BGPW7G3TVIZAHN","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":"2bc4c368c44edd0bca00dc644115e3039244a50a0eb799e0161c7a27857cb5ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T08:06:41Z","title_canon_sha256":"82aea0cc87d28397207494098ae9bd408dfb41c10dc798027f5ce2682742b9da"},"schema_version":"1.0","source":{"id":"2605.13141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13141","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13141v1","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13141","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"7BFEBOB5HXO2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7BFEBOB5HXO2BGPW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7BFEBOB5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ba8670c2f22ad79764e2096d69bb0426ff3e3086803f50ba663b4a82489e36e9","target":"graph","created_at":"2026-05-18T03:08:57Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen metrics and analytical interface meaningfully capture real-world quality differences between generated code outputs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions."}],"snapshot_sha256":"f2c38f8c27f5227a46c99565098798848b09c2cdc988c439f7bee91c00d49f45"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Chinh T. Le, Jingyu Xiao, Trevor Ong Yee Siang, Yintong Huo, Yuxuan Wan","cross_cats":[],"headline":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T08:06:41Z","title":"UIBenchKit: A unified toolkit for design-to-code model evaluation"},"references":{"count":14,"internal_anchors":0,"resolved_work":14,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"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","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"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","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Meta Open Source. [n. d.]. React Documentation. https://react.dev/. Accessed: 2026-05-10","work_id":"9c35f327-9460-47e4-a364-eb8f3c1d70f5","year":2026}],"snapshot_sha256":"533df2bedf79c760985f155f57974adfe1110cfea5c367607d70d37d601fd560"},"source":{"id":"2605.13141","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:28:47.447131Z","id":"13e9ded0-04ad-4a96-a4cd-59d3a1c6de4b","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"UIBenchKit gives researchers a single platform to run and compare design-to-code models under identical conditions.","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.","weakest_assumption":"That the chosen metrics and analytical interface meaningfully capture real-world quality differences between generated code outputs."}},"verdict_id":"13e9ded0-04ad-4a96-a4cd-59d3a1c6de4b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:055334c501013248fcd547c7ef259a2e0e192e893dbec248ff067c5166b471f2","target":"record","created_at":"2026-05-18T03:08:57Z","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":"2bc4c368c44edd0bca00dc644115e3039244a50a0eb799e0161c7a27857cb5ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T08:06:41Z","title_canon_sha256":"82aea0cc87d28397207494098ae9bd408dfb41c10dc798027f5ce2682742b9da"},"schema_version":"1.0","source":{"id":"2605.13141","kind":"arxiv","version":1}},"canonical_sha256":"f84a40b83d3ddda099f6f9b73aa3203b45b39d4ce4f0f9ffa151706f8b1f973f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f84a40b83d3ddda099f6f9b73aa3203b45b39d4ce4f0f9ffa151706f8b1f973f","first_computed_at":"2026-05-18T03:08:57.415111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:57.415111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B9IK9Fmllm43NVNEfwHiRaGvWkLYp/WBA9RBgFxo+3/Z0bi6o/4gq4aqHHHO9KqZH2FCAnV+YgjyGKc3e3NqBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:57.416059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:055334c501013248fcd547c7ef259a2e0e192e893dbec248ff067c5166b471f2","sha256:ba8670c2f22ad79764e2096d69bb0426ff3e3086803f50ba663b4a82489e36e9"],"state_sha256":"1a7b481fe8a9e9bf517e0c492a414183fc393b7cfd6818c511b24fcd95390f16"}