{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FI7FJ2BOQG3IWFEYTRJG2WNR3E","short_pith_number":"pith:FI7FJ2BO","schema_version":"1.0","canonical_sha256":"2a3e54e82e81b68b14989c526d59b1d925456a28fe70eb28139e1df6b9e779c6","source":{"kind":"arxiv","id":"2410.16232","version":1},"attestation_state":"computed","paper":{"title":"Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Ryan Li, Yanzhe Zhang","submitted_at":"2024-10-21T17:39:49Z","abstract_excerpt":"Sketches are a natural and accessible medium for UI designers to conceptualize early-stage ideas. However, existing research on UI/UX automation often requires high-fidelity inputs like Figma designs or detailed screenshots, limiting accessibility and impeding efficient design iteration. To bridge this gap, we introduce Sketch2Code, a benchmark that evaluates state-of-the-art Vision Language Models (VLMs) on automating the conversion of rudimentary sketches into webpage prototypes. Beyond end-to-end benchmarking, Sketch2Code supports interactive agent evaluation that mimics real-world design w"},"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":"2410.16232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T17:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1d0ca0d9c834f3b0540af9a2faa1910fb05fa6b85b678d13ca11105a2e7c84e","abstract_canon_sha256":"1f71e46962e8dd3f92dfa10af5c598eac916cd952e52616d5329f5d9e04d7b95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:31.726054Z","signature_b64":"sUH0qu67nwvPtS3TPygBcQwlo2H9UhuWrka+iPqY00Kgg1KNN7VqYyF+2xv1Eng3msKvCFbFQnKSTLE8CXIQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a3e54e82e81b68b14989c526d59b1d925456a28fe70eb28139e1df6b9e779c6","last_reissued_at":"2026-07-05T09:23:31.725650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:31.725650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Ryan Li, Yanzhe Zhang","submitted_at":"2024-10-21T17:39:49Z","abstract_excerpt":"Sketches are a natural and accessible medium for UI designers to conceptualize early-stage ideas. However, existing research on UI/UX automation often requires high-fidelity inputs like Figma designs or detailed screenshots, limiting accessibility and impeding efficient design iteration. To bridge this gap, we introduce Sketch2Code, a benchmark that evaluates state-of-the-art Vision Language Models (VLMs) on automating the conversion of rudimentary sketches into webpage prototypes. Beyond end-to-end benchmarking, Sketch2Code supports interactive agent evaluation that mimics real-world design w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16232","kind":"arxiv","version":1},"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/2410.16232/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":"2410.16232","created_at":"2026-07-05T09:23:31.725707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16232v1","created_at":"2026-07-05T09:23:31.725707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16232","created_at":"2026-07-05T09:23:31.725707+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI7FJ2BOQG3I","created_at":"2026-07-05T09:23:31.725707+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI7FJ2BOQG3IWFEY","created_at":"2026-07-05T09:23:31.725707+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI7FJ2BO","created_at":"2026-07-05T09:23:31.725707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17104","citing_title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E","json":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E.json","graph_json":"https://pith.science/api/pith-number/FI7FJ2BOQG3IWFEYTRJG2WNR3E/graph.json","events_json":"https://pith.science/api/pith-number/FI7FJ2BOQG3IWFEYTRJG2WNR3E/events.json","paper":"https://pith.science/paper/FI7FJ2BO"},"agent_actions":{"view_html":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E","download_json":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E.json","view_paper":"https://pith.science/paper/FI7FJ2BO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16232&json=true","fetch_graph":"https://pith.science/api/pith-number/FI7FJ2BOQG3IWFEYTRJG2WNR3E/graph.json","fetch_events":"https://pith.science/api/pith-number/FI7FJ2BOQG3IWFEYTRJG2WNR3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E/action/storage_attestation","attest_author":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E/action/author_attestation","sign_citation":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E/action/citation_signature","submit_replication":"https://pith.science/pith/FI7FJ2BOQG3IWFEYTRJG2WNR3E/action/replication_record"}},"created_at":"2026-07-05T09:23:31.725707+00:00","updated_at":"2026-07-05T09:23:31.725707+00:00"}