Pith Number

pith:VIRZYC7W

pith:2025:VIRZYC7WV7SVQB7GCYHDSIEE6K

not attested not anchored not stored refs pending

UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization

Jiale Cheng, Jie Tang, Mingde Xu, Weihan Wang, Wenyi Hong, Xiaotao Gu, Xinyue Fan, Zhen Yang

UI-to-code generation improves by treating it as a closed-loop visual optimization process rather than single-pass output.

arxiv:2511.08195 v4 · 2025-11-11 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VIRZYC7WV7SVQB7GCYHDSIEE6K}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Experiments demonstrate state-of-the-art performance on UI drafting, UI polishing, and UI editing benchmarks, even outperforming larger models, with performance consistently improving through iterative visual optimization.

C2weakest assumption

That rendered visual feedback can reliably drive iterative refinement despite non-differentiability of visual objectives and noise in absolute evaluators, which RVPO is claimed to address via relative rankings.

C3one line summary

UI2Code^N turns UI-to-code into a closed-loop visual optimization process using Relative Visual Policy Optimization on a 9B model, achieving SOTA results that improve with iterations.

Formal links

2 machine-checked theorem links

Cited by

3 papers in Pith

Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts

Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

Receipt and verification

First computed	2026-06-11T01:10:29.690970Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

aa239c0bf6afe55807e6160e392084f29de865c069203dfbb6ceb59118172332

Aliases

arxiv: 2511.08195 · arxiv_version: 2511.08195v4 · doi: 10.48550/arxiv.2511.08195 · pith_short_12: VIRZYC7WV7SV · pith_short_16: VIRZYC7WV7SVQB7G · pith_short_8: VIRZYC7W

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/VIRZYC7WV7SVQB7GCYHDSIEE6K \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: aa239c0bf6afe55807e6160e392084f29de865c069203dfbb6ceb59118172332

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ad02afdc82ccd0c52fa54c78ad4658da6d27cd0928525025a3122ef7173ea72e",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-11-11T13:00:09Z",
    "title_canon_sha256": "aff2214936666d9b4032428486b47b37c33b6e0b08c5f2186b21d51894b86bf8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.08195",
    "kind": "arxiv",
    "version": 4
  }
}