SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2609.02255 · September 2026

T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation

Yan Wang, Siwei Ma, Xinyi Hou, Weiguo Lin, Junjun Si

arXiv · PDF · Open in the Atlas

Code that ran

11 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 4 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2609.02255.json · badge: /api/ran/2609.02255.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
LLMSecResearch/T2LSC-Bench canonical (classifier label)
classifier basis: census
11 ran · 4 no recorded run
FunctionStatusWhere it lives
b64_image Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/utils.py
pointer only (licence: NONE) · get_code("6dffcbdd2a296f63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

char_error_rate Ran
ran, honoured the contract we drafted
LLMSecResearch/T2LSC-Bench/evaluation/text_metrics.py
pointer only (licence: NONE) · get_code("4eff577e5da17dcd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_metrics Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/metrics.py
pointer only (licence: NONE) · get_code("fc78ddf4ce44b934")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

edit_distance Ran
ran, honoured the contract we drafted
LLMSecResearch/T2LSC-Bench/evaluation/text_metrics.py
pointer only (licence: NONE) · get_code("873b94c7cb788eca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

failed_text_judge_result Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/text_vlm_judge.py
pointer only (licence: NONE) · get_code("09ecc9fff5877b14")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

fuse_text_rendering Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/text_fusion.py
pointer only (licence: NONE) · get_code("d760afd40a56e7f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

json_dumps Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/utils.py
pointer only (licence: NONE) · get_code("e3cca9069a2a66d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_for_text_match Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/text_metrics.py
pointer only (licence: NONE) · get_code("9c5528c6e9fbd418")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_text Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/utils.py
pointer only (licence: NONE) · get_code("ee77ade1e729a87f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_jsonl Ran
ran; our contract draft was wrong, not the code
LLMSecResearch/T2LSC-Bench/evaluation/metrics.py
pointer only (licence: NONE) · get_code("64690e0ae399636c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

run_ocr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LLMSecResearch/T2LSC-Bench/evaluation/ocr_eval.py
pointer only (licence: NONE) · get_code("b4b43a33c8f43548")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

call_ssp_slr Not yet run
unverified (harvested, no recorded run)
LLMSecResearch/T2LSC-Bench/evaluation/vlm_eval.py
pointer only (licence: NONE) · get_code("75ab28d07bf4c4b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

call_text_rendering_judge Not yet run
unverified (harvested, no recorded run)
LLMSecResearch/T2LSC-Bench/evaluation/text_vlm_judge.py
pointer only (licence: NONE) · get_code("05f5e010ca70f813")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

evaluate_taa Not yet run
unverified (harvested, no recorded run)
LLMSecResearch/T2LSC-Bench/evaluation/ocr_eval.py
pointer only (licence: NONE) · get_code("93799410e3b6db01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

normalize_text_judge_result Not yet run
unverified (harvested, no recorded run)
LLMSecResearch/T2LSC-Bench/evaluation/text_vlm_judge.py
pointer only (licence: NONE) · get_code("5a088826bdf86c17")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LLMSecResearch/T2LSC-Bench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 15 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent text-to-image models have become increasingly capable of rendering explicit text, but reliable localized text control requires more than generating the correct string. In applications such as product labeling, signage, and interface design, target text should be rendered within a designated text-bearing region without altering the predefined subject identity or surrounding scene semantics. We refer to violations of this requirement as target-text-associated semantic leakage, in which target-text semantics are expressed through non-textual visual content beyond the designated anchor. Existing visual-text benchmarks primarily evaluate readability, spelling accuracy, and layout, leaving this form of semantic leakage largely unexamined. We introduce T2LSC-Bench, a controlled diagnostic benchmark comprising 50 seed subjects and 1,200 prompt cases per model, yielding 7,160 evaluated images across six models. Its factorized design varies semantic relation, scene openness, prompt mode, and language. A dual-branch protocol combines OCR-VLM text verification with structured VLM semantic judgments to measure Text-at-Anchor Accuracy (TAA), Semantic Subject Preservation (SSP), Semantic Leakage Rate (SLR), and Conditional Semantic Leakage Rate (cSLR). Under stress-test conditions, SLR increases from 1.2% to 18.1% and cSLR from 1.3% to 18.2%, whereas TAA decreases only from 91.4% to 90.9%. Anti-leakage prompting reduces SLR from 16.6% to 8.4% without degrading rendering accuracy. Human validation on 420 images shows strong agreement between automatic and adjudicated annotations. These results show that accurate text rendering does not guarantee local containment of target-text semantics.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2609.02255")
get_code_for_paper("2609.02255")
have("2609.02255")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2609.02255.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2609.02255.svg)](https://syntology.ai/paper/2609.02255)

Connect an agent — have() is free.