{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NH4D4K26JBF4XYBZJRUJ7GGLG7","short_pith_number":"pith:NH4D4K26","schema_version":"1.0","canonical_sha256":"69f83e2b5e484bcbe0394c689f98cb37d4d6f61d9f44b85e269cfdd4dec8e025","source":{"kind":"arxiv","id":"2305.14637","version":2},"attestation_state":"computed","paper":{"title":"Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Davit Soselia, Khalid Saifullah, Tianyi Zhou","submitted_at":"2023-05-24T02:17:32Z","abstract_excerpt":"Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper, we propose a novel vision-code transformer (ViCT) composed of a vision encoder processing the screenshots and a language decoder to generate the code. They are initialized by pre-trained models such as ViT/DiT and GPT-2/LLaMA but aligning the two modalities requires end-to-end finetuning, which aims to minimize the visual discrepancy between the code-rendered webpage and the original screenshot. However, the renderi"},"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":"2305.14637","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T02:17:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5d83d44a009dcf242f7d377c594bf34f10c7d50e40a032b75604628b2f9aa002","abstract_canon_sha256":"70fb74a365839a2f7797585fc5a023bc117bcb9de85939b9f96274e418b51c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:28.494401Z","signature_b64":"TnM968NU9QXD5mgQEMD7DUZVTgyMIOmp/SuIHzd60sNf4RVFU/qUAZEl1dXIRDv6pcr3itUytZ6OvKwiKgIqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69f83e2b5e484bcbe0394c689f98cb37d4d6f61d9f44b85e269cfdd4dec8e025","last_reissued_at":"2026-07-05T07:08:28.493888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:28.493888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Davit Soselia, Khalid Saifullah, Tianyi Zhou","submitted_at":"2023-05-24T02:17:32Z","abstract_excerpt":"Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper, we propose a novel vision-code transformer (ViCT) composed of a vision encoder processing the screenshots and a language decoder to generate the code. They are initialized by pre-trained models such as ViT/DiT and GPT-2/LLaMA but aligning the two modalities requires end-to-end finetuning, which aims to minimize the visual discrepancy between the code-rendered webpage and the original screenshot. However, the renderi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14637","kind":"arxiv","version":2},"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/2305.14637/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":"2305.14637","created_at":"2026-07-05T07:08:28.493943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14637v2","created_at":"2026-07-05T07:08:28.493943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14637","created_at":"2026-07-05T07:08:28.493943+00:00"},{"alias_kind":"pith_short_12","alias_value":"NH4D4K26JBF4","created_at":"2026-07-05T07:08:28.493943+00:00"},{"alias_kind":"pith_short_16","alias_value":"NH4D4K26JBF4XYBZ","created_at":"2026-07-05T07:08:28.493943+00:00"},{"alias_kind":"pith_short_8","alias_value":"NH4D4K26","created_at":"2026-07-05T07:08:28.493943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18591","citing_title":"SPRITE: From Static Mockups to Engine-Ready Game UI","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7","json":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7.json","graph_json":"https://pith.science/api/pith-number/NH4D4K26JBF4XYBZJRUJ7GGLG7/graph.json","events_json":"https://pith.science/api/pith-number/NH4D4K26JBF4XYBZJRUJ7GGLG7/events.json","paper":"https://pith.science/paper/NH4D4K26"},"agent_actions":{"view_html":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7","download_json":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7.json","view_paper":"https://pith.science/paper/NH4D4K26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14637&json=true","fetch_graph":"https://pith.science/api/pith-number/NH4D4K26JBF4XYBZJRUJ7GGLG7/graph.json","fetch_events":"https://pith.science/api/pith-number/NH4D4K26JBF4XYBZJRUJ7GGLG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7/action/storage_attestation","attest_author":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7/action/author_attestation","sign_citation":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7/action/citation_signature","submit_replication":"https://pith.science/pith/NH4D4K26JBF4XYBZJRUJ7GGLG7/action/replication_record"}},"created_at":"2026-07-05T07:08:28.493943+00:00","updated_at":"2026-07-05T07:08:28.493943+00:00"}