TECTONICdiagram
∇θ L(θ) = 0∑i=1n wixif(x) = α + βx + ε∫0∞ e−x² dx[ 1 0 ; 0 1 ]
مجاني · مفتوح المصدر · AGPL-3.0اكتب
اكتب الأوراق البحثيةالسير الذاتيةالأطروحاتمقترحات المنحالأوراق البحثية بأعباء روتينية أقل.
Oleafly مساحة عمل مجانية لسطح المكتب لكتابة الأوراق البحثية بـ LaTeX وTypst وMarkdown. ابحث عن المصادر، وأدر الاستشهادات، وشاهد ورقتك تتشكّل في مكان واحد. استعن بمساعد ذكاء اصطناعي لمراجعة قسم أو إنشاء شكل أو إصلاح بناء معطّل، مع تغييرات يمكنك مراجعتها. يبقى مشروعك في ملفات عادية تملكها، ويمكنك استخدام المحرر مع الذكاء الاصطناعي أو دونه.
E=hν
LaTeX
\[ E = h\nu \]E=hν
LaTeX
\[ E = h\nu \]−∞0+∞
∫−∞∞e−x2dx=π
LaTeX
\[ \int_{-\infty}^{\infty} e^{-x^2}\,dx = \sqrt{\pi} \]ΔG=ΔH−TΔS
LaTeX
\[ \Delta G = \Delta H - T\Delta S \]ΔG=ΔH−TΔS
LaTeX
\[ \Delta G = \Delta H - T\Delta S \]a2+b2=c2
LaTeX
\[ a^2 + b^2 = c^2 \]OleaflyTeXFix-Bench: LaTeX Repair Bench…
Compile
Auto compile
On
Off
Compile mode
Normal
Fast[draft]
Syntax checks
Check syntax before compile
Don't check syntax
Compiler (this project)
Tectonic[built in]
Auto[system TeX]
pdfLaTeX[system TeX]
XeLaTeX[system TeX]
LuaLaTeX[system TeX]
Compile error handling
Stop on first error
Try to compile despite errors
Stop compilation
Recompile from scratch
Export source (.zip)
Export as PDF
Export as Word (.docx)
Export as HTML (.html)
Export as Markdown (.md)
Export as Plain text (.txt)
main.tex
CodeVisual
1% TeXFix-Bench technical report, manuscript version 0.2.
2% Compile with: tectonic -X compile main.tex
3
4\documentclass[journal,10pt]{IEEEtran}
5\usepackage{amsmath,amssymb,booktabs,array,graphicx}
6\usepackage{xcolor,microtype,url,fontspec,newtxsf}
7\usepackage{tikz,pgfplots,balance,hyperref}
8\pgfplotsset{compat=1.18}
9\usetikzlibrary{arrows.meta,positioning,fit,backgrounds}
10
11\definecolor{accentblue}{HTML}{006D9C}
12\definecolor{accentorange}{HTML}{D55E00}
13\definecolor{accentteal}{HTML}{0F766E}
14\definecolor{slate}{HTML}{64748B}
15
16\newcommand{\CR}{\textsc{cr}}
17\newcommand{\NEM}{\textsc{nem}}
18\newcommand{\MER}{\textsc{mer}}
19
20\title{TeXFix-Bench: Engine-Grounded Evaluation of\\
21Single-Fault \LaTeX{} Compilation Repair}
22\author{\textbf{Prajwal~S.~Venkateshmurthy}\\[0.10em]
23\small Independent Researcher\\[0.12em]
24\small San Jose, CA, USA}
25
26\begin{document}
27\maketitle
28
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine~\cite{tan2024tex}.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
38\end{abstract}
39
40\begin{IEEEkeywords}
41automated program repair, \LaTeX{}, benchmark, compilation, large
42language models, reproducibility
43\end{IEEEkeywords}
44
45\section{Introduction}\label{sec:intro}
46\LaTeX{} compilation failures are a practical target for automated repair.
47A missing delimiter or misspelled control sequence can prevent a complete
48document from building, and the first reported diagnostic may be distant
49from the underlying fault. LLM-assisted writing systems now operate inside
50\LaTeX{} editors~\cite{wen2024overleafcopilot,hou2026paperdebugger}, but their
51publications do not provide a public, engine-pinned evaluation of
52compilation-failure repair.
53
54Program repair benchmarks pair a defect with an executable oracle and a
55fixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extends
56the contract to repository-scale issues~\cite{jimenez2024swebench}.
57TeXFix-Bench studies a narrower input-output contract: a system receives
58an existing broken source document and must return a repaired full source
59under a specified engine.
60
61\section{Benchmark Construction}\label{sec:construction}
62\begin{figure*}[t]
63\centering
64\begin{tikzpicture}[font=\footnotesize\sffamily,node distance=0.58cm,
65 phase/.style={rounded corners=2.5pt,line width=0.7pt,
66 minimum width=2.55cm,minimum height=0.82cm,align=center}]
67\node[source] (seed) {13 known-good\\seed documents};
68\node[transform,right=of seed] (mutate) {12 deterministic\\mutation operators};
69\node[engine,right=of mutate] (gate) {Tectonic 0.17.0\\quality gate};
70\node[artifact,right=of gate] (rows) {627 retained\\rows};
71\draw[flow] (seed) -- (mutate);
72\draw[flow] (mutate) -- (gate);
73\draw[flow] (gate) -- (rows);
74\end{tikzpicture}
75\caption{TeXFix-Bench data and evaluation flow. Construction is
76deterministic. Evaluation reuses saved candidates and reruns only local
77engine and PDF-text checks.}
78\label{fig:pipeline}
79\end{figure*}
80
81\section{Results}\label{sec:results}
82Table~\ref{tab:main} reports the aggregate outcome.
83Figure~\ref{fig:paired} shows \CR{} and \NEM{} for each system, and
84Figure~\ref{fig:contrasts} shows the published paired contrasts.
85
86\begin{table*}[t]
87\caption{Version 0.2 results on 86 distinct hard-track inputs. \CR{} is
88intention-to-treat. \MER{} and \NEM{} use the same denominatior.}
89\label{tab:main}
90\input{results/tables/main-results-v02.tex}
91\end{table*}
92
93Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs.
94Their normalized exact-match counts are 52, 66, and 59, respectively.
95
96\begin{thebibliography}{19}
97\bibitem{just2014defects4j}
98R. Just, D. Jalali, and M. D. Ernst, \emph{Defects4J: A database of existing
99faults to enable controlled testing studies for Java programs}, ISSTA, 2014.
100\bibitem{legoues2015manybugs}
101C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest,
102and W. Weimer, \emph{The ManyBugs and IntroClass benchmarks}, TSE, 2015.
103\bibitem{jimenez2024swebench}
104C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and
105K. Narasimhan, \emph{SWE-bench}, ICLR, 2024.
106\bibitem{chen2021codex}
107M. Chen et al., \emph{Evaluating large language models trained on code},
108arXiv:2107.03374, 2021.
109\bibitem{smith2015overfitting}
110E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, \emph{Is the cure worse
111than the disease? Overfitting in automated program repair}, FSE, 2015.
112\bibitem{demillo1978}
113R. A. DeMillo, R. J. Lipton, and F. G. Sayward, \emph{Hints on test data
114selection}, Computer, 1978.
115\bibitem{jia2011mutation}
116Y. Jia and M. Harman, \emph{An analysis and survey of the development of
117mutation testing}, TSE, 2011.
118\bibitem{gupta2017deepfix}
119R. Gupta, S. Pal, A. Kanade, and S. Shevade, \emph{DeepFix}, AAAI, 2017.
120\bibitem{yasunaga2020drrepair}
121M. Yasunaga and P. Liang, \emph{Graph-based, self-supervised program repair
122from diagnostic feedback}, ICML, 2020.
123\bibitem{zhu2022eqfix}
124F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, \emph{EqFix}, ASE, 2022.
125\bibitem{wang2024texocr}
126K. Wang et al., \emph{TexOCR-Bench: Benchmarking page-image-to-LaTeX
127reconstruction}, 2024.
128\bibitem{wen2024overleafcopilot}
129H. Wen, Z. Zhang, and Y. Li, \emph{OverleafCopilot: Empowering academic
130writing in Overleaf with large language models}, 2024.
131\bibitem{hou2026paperdebugger}
132S. Hou et al., \emph{PaperDebugger: An in-editor assistant for manuscript
133repair}, 2026.
134\bibitem{tan2024tex}
135J. Tan, K. Zhang, and X. Chen, \emph{Instrumenting TeX produced diagnostics
136for repair}, 2024.
137\bibitem{zheng2023judging}
138L. Zheng et al., \emph{Judging LLM-as-a-judge with MT-Bench and Chatbot
139Arena}, NeurIPS, 2023.
140\bibitem{panickssery2024selfpref}
141A. Panickssery, S. R. Bowman, and S. Feng, \emph{LLM evaluators recognize
142and favor their own generations}, NeurIPS, 2024.
143\bibitem{hui2024qwen}
144B. Hui et al., \emph{Qwen2.5-Coder technical report}, 2024.
145\bibitem{metaai2024llama}
146Meta AI, \emph{The Llama 3 herd of models}, 2024.
147\bibitem{kassis2024reproduce}
148E. Kassis et al., \emph{On the reproducibility of research artifacts}, 2024.
149\end{thebibliography}
150
151\end{document}
Logs
1.9s
100%
1
of 2
Compiling
1/3 done
1 running · 1 queued
- Language analysisCurrent project revision analyzed
- CompilingProducing and verifying PDF output
- Rendering PDFWaiting for verified compile output
TeXFix-Bench: Engine-Grounded Evaluation of
Single-Fault LATEX Compilation Repair
Single-Fault LATEX Compilation Repair
Prajwal S. Venkateshmurthy
Independent Researcher
San Jose, CA, USA
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
I. INTRODUCTION
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
II. RELATED WORK
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
III. TASK AND SCOPE
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
CR = compile(c) ∧ LCStok(Tc, Tr) ≥ 0.80(1)
IV. BENCHMARK CONSTRUCTION
Fig. 1. TeXFix-Bench data and evaluation flow. Construction is deterministic.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
V. EVALUATION METHOD
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
TABLE I
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Fig. 2. Compile Recovery and normalized exact match on the fixed cohort of n = 86 hard-track inputs. Circles denote CR, squares NEM.
VI. RESULTS
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
VII. CONCLUSION
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
REFERENCES
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
Zoom in
Zoom out
Fit to width
Fit to height
Reset to 100%
25%
50%
75%
100%
150%
200%
400%
Undefined reference
bibentry · legoues2015manybug
@article
ibitem{legoues2015manybugs}
main.tex:956
ibitem{legoues2015manybugs}
main.tex:956
Oleafly AgentCLI Agent BETA
- Steps
- 1
- Input
- 5,144
- Output
- 467
- Runs
- 1
- Steps
- 3
- Tokens
- 39,035
Costs are estimates based on public model pricing, not billing totals.
Connect an AI provider to continue
Bring your own API key (OpenAI, Anthropic, Groq, and more) or run a model locally with Ollama. The assistant can read and edit files, compile your project, and verify the PDF.
Connect a providerRun a local model with Ollama
What would you like to do today?Working on "TeXFix-Bench: LaTeX Repair Bench..."
ResearchAuthoringFiguresReviewSubmissionCommunicationToolingYour skills
Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.
oleafly-literature-sweep oleafly-research-loop paper-lookup research-lookup oleafly-literature-sweep
What would you like to do today?
Working on "TeXFix-Bench: LaTeX Repair Bench..."
Check the introduction for unsupported claims. Do not edit files.
Claude Code
Read main.tex
Read references.bib
The energy-use comparison needs a supporting source. I found the claim in the introduction, but its citation covers detection accuracy. Your files are unchanged.
Sweep the literature for this project
Working...
Thinking...
Thought for 10s
update todos
Explored 3 files
Read file
Read file
Read file
I'll inspect the current citations first, then search for papers that actually support the claims.
Working...
Thinking...
I need sources that match the paper's actual claims:
- satellite fire detection
- low-power sensor networks
- TinyML and quantized inference
I'll keep only results with verifiable DOI metadata.
- satellite fire detection
- low-power sensor networks
- TinyML and quantized inference
I'll keep only results with verifiable DOI metadata.
Search literature
Search literature
Search papers
Quick audit: three citation keys do not resolve, and two existing entries point to unrelated papers. I'm searching for better matches on wildfire sensing, TinyML, and low-power networks.
Working...
Search literature
Search literature
Check citation
Check citation
Four solid matches so far: MODIS fire detection, a field-tested sensor-network detector, an energy-harvesting survey, and a TinyML review. I'm checking the DOI metadata before I touch the bibliography.
Working...
Check citation
update todos
The citations check out. I'll add nine verified entries to references.bib, then place them beside the claims they support.
Working...
write fileApproved
The bibliography is in place. Next I'm replacing the unresolved keys in main.tex with the verified sources.
Working...
replace in fileApproved
Compile document
Check PDF pages
Done. I added nine verified references, replaced the three unresolved keys, and recompiled the paper. The two-page PDF now has a complete IEEE bibliography with no missing citations.
Compiled and checked the rendered PDF
STEP 1/6
Plan
Inventory citations used in main.tex and references.bib
Search literature for papers matching each cited claim
Verify every candidate citation is real
Add verified BibTeX entries to references.bib
Replace unresolved cites in main.tex
Recompile and confirm all citations resolve
The assistant wants to change your files
write_filereferences.bibline 1
references.bibfirst change · L11
@article{open_science2015,2
title = {Estimating the Reproducibility of Psychological Science},1
@article{giglio2003,2
author = {Giglio, Louis and Descloitres, Jacques and Justice, Christopher O.},3
title = {An Enhanced Contextual Fire Detection Algorithm for {MODIS}},4
journal = {Remote Sensing of Environment},5
year = {2003}, doi = {10.1016/S0034-4257(03)00184-6}6
} Reject Approve
The assistant wants to change your files
replace_in_filemain.texline 21
main.texfirst change · L2154
Program repair benchmarks pair a defect with an executable oracle and a55
fixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extends55
fixed harness~\cite{just2014defects4j,legoues2015manybugs}. SWE-bench extends56
the contract to repository-scale issues~\cite{jimenez2024swebench}.57
TeXFix-Bench studies a narrower contract: a system receives an existing57
TeXFix-Bench studies a narrower contract~\cite{zhu2022eqfix}: a system receives Reject Approve
Claude Code
Start or reconnect a conversation to send a message Start a conversation with Claude Code
Ask AI to help with your document...
Ask for approval Prompts Persona gpt-5.6-sol
Logs
4.3s
105%
1of 2
TeXFix-Bench: Engine-Grounded Evaluation of
Single-Fault LATEX Compilation Repair
Single-Fault LATEX Compilation Repair
Prajwal S. Venkateshmurthy
Independent Researcher
San Jose, CA, USA
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
I. INTRODUCTION
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
II. RELATED WORK
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
III. TASK AND SCOPE
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
CR = compile(c) ∧ LCStok(Tc, Tr) ≥ 0.80(1)
IV. BENCHMARK CONSTRUCTION
Fig. 1. TeXFix-Bench data and evaluation flow. Construction is deterministic.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
V. EVALUATION METHOD
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
TABLE I
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Fig. 2. Compile Recovery and normalized exact match on the fixed cohort of n = 86 hard-track inputs. Circles denote CR, squares NEM.
VI. RESULTS
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
VII. CONCLUSION
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
REFERENCES
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
Stale
references.bib
1
@article{giglio2003,2
title = {An Enhanced Contextual Fire Detection Algorithm for MODIS},3
year = {2003},4
}6
@article{schroeder2014,7
title = {The New VIIRS 375 m Active Fire Detection Data Product},8
year = {2014},9
}11
@article{dampage2022,12
title = {Forest Fire Detection System Using Wireless Sensor Networks},13
year = {2022},14
}16
@article{adumanu2018,17
title = {Energy-Harvesting Wireless Sensor Networks: A Review},18
year = {2018},19
}21
@article{adelantado2017,22
title = {Understanding the Limits of LoRaWAN},23
year = {2017},24
}26
@article{bai2018,27
title = {An Empirical Evaluation of Generic Convolutional Networks},28
year = {2018},29
}31
@article{jacob2018,32
title = {Quantization and Training of Neural Networks},33
year = {2018},34
}36
@article{ray2022,37
title = {A Review on TinyML},38
year = {2022},39
}41
@article{geifman2017,42
title = {Selective Classification for Deep Neural Networks},43
year = {2017},44
}Providers and keysCLI agentsInstructionsPersonasSkillsMCP
Connect any providers you use below. Keys are stored locally only. Saving one sets it as the default.
You can switch between configured providers and models from the dropdown in the chat panel.
OpenAI
ConnectedGet key
GPT models. The default choice.
Paste your API key here••••••••••••••••••••••••••••••••••••••••••••••
Save
Checking key...Key valid. Models are ready below.
Modelgpt-5.6-sol
Replace key
Models Refresh
gpt-5.6-sol
gpt-5.6-terra
gpt-5.6-luna
gpt-5.5-pro
gpt-5.5
gpt-5.4
Anthropic
Google Gemini
Z.AI (GLM Coding Plan)
Groq
OpenRouter
DeepSeek
Mistral
xAI (Grok)
Perplexity
Ollama (local)
Model data updated Sep 3, 2026, from the last download
Refresh
Add custom provider
Default chat model
Used whenever you start a new chat. You can still switch models for an individual conversation from the chat panel.
gpt-5.6-sol
OpenAI
gpt-5.6-sol
gpt-5.6-terra
gpt-5.6-luna
gpt-5.5-pro
gpt-5.5
gpt-5.4
gpt-5.4-mini
gpt-5.3
gpt-5.3-mini
gpt-4.1
Custom instructions
Added to every AI request as your personal style and preferences. The assistant follows these on top of its built-in behavior. They can't override its tools or safety rules.
e.g. Review for venue style, verify citations, and never invent bibliographic metadata.
Save instructions SavedAgent capabilities
Allow PDF page capture for AILets the agent rasterize compiled pages for vision layout checks. Disable if you prefer not to send page images to your provider.
The assistant currently supports these tools
main.tex
CodeVisual
1% TeXFix-Bench technical report, manuscript version 0.2.
2% Compile with: tectonic -X compile main.tex
3
4\documentclass[journal,10pt]{IEEEtran}
5\usepackage{amsmath,amssymb,booktabs,array,graphicx}
6\usepackage{xcolor,microtype,url,fontspec,newtxsf}
7\usepackage{tikz,pgfplots,balance,hyperref}
8\pgfplotsset{compat=1.18}
9\usetikzlibrary{arrows.meta,positioning,fit,backgrounds}
10
11\definecolor{accentblue}{HTML}{006D9C}
12\definecolor{accentorange}{HTML}{D55E00}
13\definecolor{accentteal}{HTML}{0F766E}
14\definecolor{slate}{HTML}{64748B}
15
16\newcommand{\CR}{\textsc{cr}}
17\newcommand{\NEM}{\textsc{nem}}
18\newcommand{\MER}{\textsc{mer}}
19
20\title{TeXFix-Bench: Engine-Grounded Evaluation of\\
21Single-Fault \LaTeX{} Compilation Repair}
22\author{\textbf{Prajwal~S.~Venkateshmurthy}\\[0.10em]
23\small Independent Researcher\\[0.12em]
24\small San Jose, CA, USA}
25
26\begin{document}
27\maketitle
28
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine~\cite{tan2024tex}.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
38\end{abstract}
39
40\begin{IEEEkeywords}
41automated program repair, \LaTeX{}, benchmark, compilation, large
42language models, reproducibility
43\end{IEEEkeywords}
44
45\section{Introduction}\label{sec:intro}
46\LaTeX{} compilation failures are a practical target for automated repair.
47A missing delimiter or misspelled control sequence can prevent a complete
48document from building, and the first reported diagnostic may be distant
49from the underlying fault. LLM-assisted writing systems now operate inside
50\LaTeX{} editors~\cite{wen2024overleafcopilot,hou2026paperdebugger}, but their
51publications do not provide a public, engine-pinned evaluation of
52compilation-failure repair.
53
54Program repair benchmarks pair a defect with an executable oracle and a
55fixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extends
56the contract to repository-scale issues~\cite{jimenez2024swebench}.
57TeXFix-Bench studies a narrower input-output contract: a system receives
58an existing broken source document and must return a repaired full source
59under a specified engine.
60
61\section{Benchmark Construction}\label{sec:construction}
62\begin{figure*}[t]
63\centering
64\begin{tikzpicture}[font=\footnotesize\sffamily,node distance=0.58cm,
65 phase/.style={rounded corners=2.5pt,line width=0.7pt,
66 minimum width=2.55cm,minimum height=0.82cm,align=center}]
67\node[source] (seed) {13 known-good\\seed documents};
68\node[transform,right=of seed] (mutate) {12 deterministic\\mutation operators};
69\node[engine,right=of mutate] (gate) {Tectonic 0.17.0\\quality gate};
70\node[artifact,right=of gate] (rows) {627 retained\\rows};
71\draw[flow] (seed) -- (mutate);
72\draw[flow] (mutate) -- (gate);
73\draw[flow] (gate) -- (rows);
74\end{tikzpicture}
75\caption{TeXFix-Bench data and evaluation flow. Construction is
76deterministic. Evaluation reuses saved candidates and reruns only local
77engine and PDF-text checks.}
78\label{fig:pipeline}
79\end{figure*}
80
81\section{Results}\label{sec:results}
82Table~\ref{tab:main} reports the aggregate outcome.
83Figure~\ref{fig:paired} shows \CR{} and \NEM{} for each system, and
84Figure~\ref{fig:contrasts} shows the published paired contrasts.
85
86\begin{table*}[t]
87\caption{Version 0.2 results on 86 distinct hard-track inputs. \CR{} is
88intention-to-treat. \MER{} and \NEM{} use the same denominatior.}
89\label{tab:main}
90\input{results/tables/main-results-v02.tex}
91\end{table*}
92
93Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs.
94Their normalized exact-match counts are 52, 66, and 59, respectively.
95
96\begin{thebibliography}{19}
97\bibitem{just2014defects4j}
98R. Just, D. Jalali, and M. D. Ernst, \emph{Defects4J: A database of existing
99faults to enable controlled testing studies for Java programs}, ISSTA, 2014.
100\bibitem{legoues2015manybugs}
101C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest,
102and W. Weimer, \emph{The ManyBugs and IntroClass benchmarks}, TSE, 2015.
103\bibitem{jimenez2024swebench}
104C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and
105K. Narasimhan, \emph{SWE-bench}, ICLR, 2024.
106\bibitem{chen2021codex}
107M. Chen et al., \emph{Evaluating large language models trained on code},
108arXiv:2107.03374, 2021.
109\bibitem{smith2015overfitting}
110E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, \emph{Is the cure worse
111than the disease? Overfitting in automated program repair}, FSE, 2015.
112\bibitem{demillo1978}
113R. A. DeMillo, R. J. Lipton, and F. G. Sayward, \emph{Hints on test data
114selection}, Computer, 1978.
115\bibitem{jia2011mutation}
116Y. Jia and M. Harman, \emph{An analysis and survey of the development of
117mutation testing}, TSE, 2011.
118\bibitem{gupta2017deepfix}
119R. Gupta, S. Pal, A. Kanade, and S. Shevade, \emph{DeepFix}, AAAI, 2017.
120\bibitem{yasunaga2020drrepair}
121M. Yasunaga and P. Liang, \emph{Graph-based, self-supervised program repair
122from diagnostic feedback}, ICML, 2020.
123\bibitem{zhu2022eqfix}
124F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, \emph{EqFix}, ASE, 2022.
125\bibitem{wang2024texocr}
126K. Wang et al., \emph{TexOCR-Bench: Benchmarking page-image-to-LaTeX
127reconstruction}, 2024.
128\bibitem{wen2024overleafcopilot}
129H. Wen, Z. Zhang, and Y. Li, \emph{OverleafCopilot: Empowering academic
130writing in Overleaf with large language models}, 2024.
131\bibitem{hou2026paperdebugger}
132S. Hou et al., \emph{PaperDebugger: An in-editor assistant for manuscript
133repair}, 2026.
134\bibitem{tan2024tex}
135J. Tan, K. Zhang, and X. Chen, \emph{Instrumenting TeX produced diagnostics
136for repair}, 2024.
137\bibitem{zheng2023judging}
138L. Zheng et al., \emph{Judging LLM-as-a-judge with MT-Bench and Chatbot
139Arena}, NeurIPS, 2023.
140\bibitem{panickssery2024selfpref}
141A. Panickssery, S. R. Bowman, and S. Feng, \emph{LLM evaluators recognize
142and favor their own generations}, NeurIPS, 2024.
143\bibitem{hui2024qwen}
144B. Hui et al., \emph{Qwen2.5-Coder technical report}, 2024.
145\bibitem{metaai2024llama}
146Meta AI, \emph{The Llama 3 herd of models}, 2024.
147\bibitem{kassis2024reproduce}
148E. Kassis et al., \emph{On the reproducibility of research artifacts}, 2024.
149\end{thebibliography}
150
151\end{document}
Logs
1.9s
100%
1
of 2
Compiling
1/3 done
1 running · 1 queued
- Language analysisCurrent project revision analyzed
- CompilingProducing and verifying PDF output
- Rendering PDFWaiting for verified compile output
TeXFix-Bench: Engine-Grounded Evaluation of
Single-Fault LATEX Compilation Repair
Single-Fault LATEX Compilation Repair
Prajwal S. Venkateshmurthy
Independent Researcher
San Jose, CA, USA
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
I. INTRODUCTION
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
II. RELATED WORK
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
III. TASK AND SCOPE
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
CR = compile(c) ∧ LCStok(Tc, Tr) ≥ 0.80(1)
IV. BENCHMARK CONSTRUCTION
Fig. 1. TeXFix-Bench data and evaluation flow. Construction is deterministic.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
V. EVALUATION METHOD
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
TABLE I
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Fig. 2. Compile Recovery and normalized exact match on the fixed cohort of n = 86 hard-track inputs. Circles denote CR, squares NEM.
VI. RESULTS
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
VII. CONCLUSION
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
REFERENCES
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
Zoom in
Zoom out
Fit to width
Fit to height
Reset to 100%
25%
50%
75%
100%
150%
200%
400%
Work stays in a separate workspace until you review and apply it.
A blank task
Claude CodeCLI agent · uses its own account
Review wildfire sensing literature Claude CodeRunning
Find papers on low-power wildfire sensing. Save a reading list with verified DOIs.
Task startedWorking in a separate copy of the project
Read main.tex and references.bibIdentify the claims and existing sources
Search literatureLow-power sensing · wildfire detection · sensor networks
Verify citation identifiersCross-check DOI metadata and remove duplicates
Saved reading listresearch/reading-list.md
Ready for reviewOne new file. The manuscript is unchanged.
Staged copy · source f4a9c21
The original project stays unchanged until you apply reviewed files.
Preview every selected file before applying it.
research/reading-list.mdAddedPreview+ # Wildfire sensing: reading list + + ## Satellite fire detection + Giglio et al. (2003). An Enhanced Contextual Fire + Detection Algorithm for MODIS. + DOI: 10.1016/S0034-4257(03)00184-6 + + Use: background on satellite detection methods. + Check separately: claims about ground-sensor energy use.
Completedresearch/reading-list.md is in your project.
Oleafly›diagram.tikz
Drag Shapes to Move · Drag Handles to Connect · Space + Drag to Pan · Double-Click to Edit Text
Output Probabilities
Softmax
Linear
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
N×
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
Add & Norm
Masked Multi-Head
Attention
Attention
N×
+
Positional Encoding
Input Embedding
Inputs
+
Positional Encoding
Output Embedding
Outputs (shifted right)
Snippets □ ○ → — { }
1
\definecolor{c0F172A}{HTML}{0F172A}2
\definecolor{c1E293B}{HTML}{1E293B}3
\definecolor{cC7C7CC}{HTML}{C7C7CC}4
\definecolor{cCDEDD0}{HTML}{CDEDD0}5
\definecolor{cCFE8F8}{HTML}{CFE8F8}6
\definecolor{cDAD2F0}{HTML}{DAD2F0}7
\definecolor{cE9E9EC}{HTML}{E9E9EC}8
\definecolor{cEEF2C3}{HTML}{EEF2C3}9
\definecolor{cF9D7D9}{HTML}{F9D7D9}10
\definecolor{cFDE3C7}{HTML}{FDE3C7}11
\definecolor{cFFFFFF}{HTML}{FFFFFF}12
\begin{tikzpicture}[>={Triangle[length=0.313cm,width=0.313cm]}]13
\node (n1_mds37) at (6.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Inputs};14
\node (n2_hnw3j) at (6.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Input Embedding};15
\node (n3_x9vjf) at (4.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {};16
\node (n4_aa0b6) at (6.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+};17
\node (n5_lbeum) at (2.625,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding};18
\node (n6_gr85r) at (6.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention};19
\node (n7_it3d0) at (6.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};20
\node (n8_0ae9p) at (6.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward};21
\node (n9_31jhg) at (6.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};22
\node (n11_3mv5b) at (1.875,-13.575) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×};23
\node (n12_y6hil) at (16.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Outputs (shifted right)};24
\node (n13_oukbf) at (16.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Output Embedding};25
\node (n14_e6m10) at (16.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+};26
\node (n15_te7fn) at (18.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {};27
\node (n16_otz7n) at (19.875,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding};28
\node (n17_nw4kz) at (16.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Masked Multi-Head Attention};29
\node (n18_feep8) at (16.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};30
\node (n19_9lw0g) at (16.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention};31
\node (n20_lz6h6) at (16.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};32
\node (n21_iyi8d) at (16.25,-8.825) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward};33
\node (n22_hapki) at (16.25,-7.075) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};34
\node (n24_qwbl3) at (19.375,-11.825) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×};35
\node (n25_isnp1) at (16.25,-4.8) [draw=c1E293B, line width=0.025cm, fill=cDAD2F0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Linear};36
\node (n26_ggail) at (16.25,-2.8) [draw=c1E293B, line width=0.025cm, fill=cCDEDD0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Softmax};37
\node (n27_76g5v) at (16.25,-0.875) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.5cm, minimum height=1.25cm] {Output Probabilities};38
\begin{scope}[on background layer]39
\node (n10_ma9el) at (6.25,-13.575) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=7.65cm] {};40
\node (n23_egiii) at (16.25,-11.7) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=11.4cm] {};41
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-21.25) -- (6.25,-20.75) -- (6.25,-21.15) -- (6.25,-20.65);42
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-19.5) -- (6.25,-19) -- (6.25,-19.1) -- (6.25,-18.6);43
\draw[->, line width=0.05cm] (n3_x9vjf.east) to[out=0, in=180] (n4_aa0b6.west);44
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-17.75) -- (6.25,-17.25) -- (6.25,-17.4) -- (6.25,-16.9);45
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-15.75) -- (6.25,-15.25) -- (6.25,-15.65) -- (6.25,-15.15);46
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-14) -- (6.25,-13.5) -- (6.25,-13.65) -- (6.25,-13.15);47
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-12) -- (6.25,-11.5) -- (6.25,-11.9) -- (6.25,-11.4);48
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-21.25) -- (16.25,-20.75) -- (16.25,-21.15) -- (16.25,-20.65);49
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-19.5) -- (16.25,-19) -- (16.25,-19.1) -- (16.25,-18.6);50
\draw[->, line width=0.05cm] (n15_te7fn.west) to[out=180, in=0] (n14_e6m10.east);51
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-17.75) -- (16.25,-17.25) -- (16.25,-17.4) -- (16.25,-16.9);52
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-15.75) -- (16.25,-15.25) -- (16.25,-15.65) -- (16.25,-15.15);53
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-14) -- (16.25,-13.5) -- (16.25,-13.65) -- (16.25,-13.15);54
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-12) -- (16.25,-11.5) -- (16.25,-11.9) -- (16.25,-11.4);55
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-10.25) -- (16.25,-9.75) -- (16.25,-9.9) -- (16.25,-9.4);56
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-8.25) -- (16.25,-7.75) -- (16.25,-8.15) -- (16.25,-7.65);57
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-6.5) -- (16.25,-6) -- (16.25,-5.925) -- (16.25,-5.85) -- (16.25,-5.35);58
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-4.25) -- (16.25,-3.75) -- (16.25,-3.85) -- (16.25,-3.35);59
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-2.25) -- (16.25,-1.75) -- (16.25,-2) -- (16.25,-1.5);60
\draw[->, line width=0.05cm, rounded corners=0.125cm] (8.375,-10.825) -- (8.875,-10.825) -- (11.25,-10.825) -- (11.25,-12.575) -- (13.625,-12.575) -- (14.125,-12.575);61
\draw[->, line width=0.05cm, rounded corners=0.125cm] (5.825,-18.175) -- (5.325,-18.175) -- (3.625,-18.175) -- (3.625,-14.575) -- (4.125,-14.575);62
\draw[->, line width=0.05cm, rounded corners=0.125cm] (4.125,-14.575) -- (4.1,-14.575) -- (3.625,-14.575) -- (3.625,-10.825) -- (4.125,-10.825);63
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.675,-18.175) -- (17.175,-18.175) -- (18.875,-18.175) -- (18.875,-14.575) -- (18.375,-14.575);64
\draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-14.575) -- (18.875,-14.575) -- (18.875,-10.825) -- (18.4,-10.825) -- (18.375,-10.825);65
\draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-10.825) -- (18.875,-10.825) -- (18.875,-7.075) -- (18.4,-7.075) -- (18.375,-7.075);66
\end{scope}67
\end{tikzpicture}PREVIEWPNG scale2x ⌄Background
Output Probabilities
Softmax
Linear
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
N×
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
Add & Norm
Masked Multi-Head
Attention
Attention
N×
+
Positional Encoding
Input Embedding
Inputs
+
Positional Encoding
Output Embedding
Outputs (shifted right)
Compiling...
New project
Attention Is All You NeedFederated Learning Data FlowCatalyst Screening Data ReportMangrove Canopy Drone SurveyNSF Progress Report — Year 2
Save to project Save Figure
Search 12 projects by name, ID, main file, color, or export
TECTONICCatalyst Screening Data Report
DocumentUpdated Jul 15
TECTONICAlex Chen - Google Resume
ResumeUpdated Jul 15
TECTONICSleep and Memory Consolidation — Evidence Map
DocumentUpdated Jul 14
TECTONICTeXFix-Bench: LaTeX Repair Benchmark
DocumentUpdated Jul 13
TECTONICNeural Operators for Parametric PDEs
DocumentUpdated Jul 13
TECTONICTheo Martins — HCI Researcher Resume
ResumeUpdated Jul 12
TECTONICieee-journal
DocumentUpdated Jul 12
TECTONICMapping Pollinator Corridors — Research Poster
DocumentUpdated Jul 29
TYPSTArjun Rao — Computational Linguistics CV
ResumeUpdated Jul 11
TECTONICDextrous Manipulation — Proposal
DocumentUpdated Jul 9
TECTONICStatistical Consulting Report
DocumentUpdated Jun 25
Oleafly›diagram
Snippets □ ○ → — { }
1
\definecolor{c0F172A}{HTML}{0F172A}2
\definecolor{c1E293B}{HTML}{1E293B}3
\definecolor{cC7C7CC}{HTML}{C7C7CC}4
\definecolor{cCDEDD0}{HTML}{CDEDD0}5
\definecolor{cCFE8F8}{HTML}{CFE8F8}6
\definecolor{cDAD2F0}{HTML}{DAD2F0}7
\definecolor{cE9E9EC}{HTML}{E9E9EC}8
\definecolor{cEEF2C3}{HTML}{EEF2C3}9
\definecolor{cF9D7D9}{HTML}{F9D7D9}10
\definecolor{cFDE3C7}{HTML}{FDE3C7}11
\definecolor{cFFFFFF}{HTML}{FFFFFF}12
\begin{tikzpicture}[>={Triangle[length=0.313cm,width=0.313cm]}]13
\node (n1_mds37) at (6.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Inputs};14
\node (n2_hnw3j) at (6.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Input Embedding};15
\node (n3_x9vjf) at (4.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {};16
\node (n4_aa0b6) at (6.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+};17
\node (n5_lbeum) at (2.625,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding};18
\node (n6_gr85r) at (6.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention};19
\node (n7_it3d0) at (6.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};20
\node (n8_0ae9p) at (6.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward};21
\node (n9_31jhg) at (6.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};22
\node (n11_3mv5b) at (1.875,-13.575) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×};23
\node (n12_y6hil) at (16.25,-21.75) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1cm] {Outputs (shifted right)};24
\node (n13_oukbf) at (16.25,-20.075) [draw=c1E293B, line width=0.025cm, fill=cF9D7D9, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Output Embedding};25
\node (n14_e6m10) at (16.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {+};26
\node (n15_te7fn) at (18.25,-18.175) [circle, draw=c1E293B, line width=0.025cm, fill=cFFFFFF, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=0.85cm, minimum height=0.85cm] {};27
\node (n16_otz7n) at (19.875,-19.375) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=3.5cm, minimum height=1cm] {Positional Encoding};28
\node (n17_nw4kz) at (16.25,-16.325) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Masked Multi-Head Attention};29
\node (n18_feep8) at (16.25,-14.575) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};30
\node (n19_9lw0g) at (16.25,-12.575) [draw=c1E293B, line width=0.025cm, fill=cFDE3C7, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Multi-Head Attention};31
\node (n20_lz6h6) at (16.25,-10.825) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};32
\node (n21_iyi8d) at (16.25,-8.825) [draw=c1E293B, line width=0.025cm, fill=cCFE8F8, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Feed Forward};33
\node (n22_hapki) at (16.25,-7.075) [draw=c1E293B, line width=0.025cm, fill=cEEF2C3, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.15cm] {Add \& Norm};34
\node (n24_qwbl3) at (19.375,-11.825) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=1.25cm, minimum height=0.75cm] {N×};35
\node (n25_isnp1) at (16.25,-4.8) [draw=c1E293B, line width=0.025cm, fill=cDAD2F0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Linear};36
\node (n26_ggail) at (16.25,-2.8) [draw=c1E293B, line width=0.025cm, fill=cCDEDD0, rounded corners=0.1cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.25cm, minimum height=1.1cm] {Softmax};37
\node (n27_76g5v) at (16.25,-0.875) [text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=4.5cm, minimum height=1.25cm] {Output Probabilities};38
\begin{scope}[on background layer]39
\node (n10_ma9el) at (6.25,-13.575) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=7.65cm] {};40
\node (n23_egiii) at (16.25,-11.7) [draw=cC7C7CC, line width=0.025cm, fill=cE9E9EC, rounded corners=0.4cm, text=c0F172A, font=\rmfamily\fontsize{10}{12}\selectfont, inner sep=0pt, outer sep=0pt, minimum width=5.5cm, minimum height=11.4cm] {};41
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-21.25) -- (6.25,-20.75) -- (6.25,-21.15) -- (6.25,-20.65);42
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-19.5) -- (6.25,-19) -- (6.25,-19.1) -- (6.25,-18.6);43
\draw[->, line width=0.05cm] (n3_x9vjf.east) to[out=0, in=180] (n4_aa0b6.west);44
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-17.75) -- (6.25,-17.25) -- (6.25,-17.4) -- (6.25,-16.9);45
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-15.75) -- (6.25,-15.25) -- (6.25,-15.65) -- (6.25,-15.15);46
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-14) -- (6.25,-13.5) -- (6.25,-13.65) -- (6.25,-13.15);47
\draw[->, line width=0.05cm, rounded corners=0.125cm] (6.25,-12) -- (6.25,-11.5) -- (6.25,-11.9) -- (6.25,-11.4);48
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-21.25) -- (16.25,-20.75) -- (16.25,-21.15) -- (16.25,-20.65);49
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-19.5) -- (16.25,-19) -- (16.25,-19.1) -- (16.25,-18.6);50
\draw[->, line width=0.05cm] (n15_te7fn.west) to[out=180, in=0] (n14_e6m10.east);51
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-17.75) -- (16.25,-17.25) -- (16.25,-17.4) -- (16.25,-16.9);52
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-15.75) -- (16.25,-15.25) -- (16.25,-15.65) -- (16.25,-15.15);53
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-14) -- (16.25,-13.5) -- (16.25,-13.65) -- (16.25,-13.15);54
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-12) -- (16.25,-11.5) -- (16.25,-11.9) -- (16.25,-11.4);55
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-10.25) -- (16.25,-9.75) -- (16.25,-9.9) -- (16.25,-9.4);56
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-8.25) -- (16.25,-7.75) -- (16.25,-8.15) -- (16.25,-7.65);57
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-6.5) -- (16.25,-6) -- (16.25,-5.925) -- (16.25,-5.85) -- (16.25,-5.35);58
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-4.25) -- (16.25,-3.75) -- (16.25,-3.85) -- (16.25,-3.35);59
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.25,-2.25) -- (16.25,-1.75) -- (16.25,-2) -- (16.25,-1.5);60
\draw[->, line width=0.05cm, rounded corners=0.125cm] (8.375,-10.825) -- (8.875,-10.825) -- (11.25,-10.825) -- (11.25,-12.575) -- (13.625,-12.575) -- (14.125,-12.575);61
\draw[->, line width=0.05cm, rounded corners=0.125cm] (5.825,-18.175) -- (5.325,-18.175) -- (3.625,-18.175) -- (3.625,-14.575) -- (4.125,-14.575);62
\draw[->, line width=0.05cm, rounded corners=0.125cm] (4.125,-14.575) -- (4.1,-14.575) -- (3.625,-14.575) -- (3.625,-10.825) -- (4.125,-10.825);63
\draw[->, line width=0.05cm, rounded corners=0.125cm] (16.675,-18.175) -- (17.175,-18.175) -- (18.875,-18.175) -- (18.875,-14.575) -- (18.375,-14.575);64
\draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-14.575) -- (18.875,-14.575) -- (18.875,-10.825) -- (18.4,-10.825) -- (18.375,-10.825);65
\draw[->, line width=0.05cm, rounded corners=0.125cm] (18.375,-10.825) -- (18.875,-10.825) -- (18.875,-7.075) -- (18.4,-7.075) -- (18.375,-7.075);66
\end{scope}67
\end{tikzpicture}Drag Shapes to Move · Drag Handles to Connect · Space + Drag to Pan · Double-Click to Edit Text
Output Probabilities
Softmax
Linear
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
N×
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
Add & Norm
Masked Multi-Head
Attention
Attention
N×
+
Positional Encoding
Input Embedding
Inputs
+
Positional Encoding
Output Embedding
Outputs (shifted right)
▤ Logs ✓ 1.4s⌗ − 131%⌄ ＋ ◐ ↻
Output Probabilities
Softmax
Linear
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
N×
Add & Norm
Feed Forward
Add & Norm
Multi-Head Attention
Add & Norm
Masked Multi-Head
Attention
Attention
N×
+
Positional Encoding
Input Embedding
Inputs
+
Positional Encoding
Output Embedding
Outputs (shifted right)
Export source (.zip) Export as PDF (vector image) Export as PNG (raster image)
✓Saved to figures/diagram.png
diagram.png
📁 Desktop ⌃
main.tex
CodeVisual
1% TeXFix-Bench technical report, manuscript version 0.2.
2% Compile with: tectonic -X compile main.tex
3
4\documentclass[journal,10pt]{IEEEtran}
5\usepackage{amsmath,amssymb,booktabs,array,graphicx}
6\usepackage{xcolor,microtype,url,fontspec,newtxsf}
7\usepackage{tikz,pgfplots,balance,hyperref}
8\pgfplotsset{compat=1.18}
9\usetikzlibrary{arrows.meta,positioning,fit,backgrounds}
10
11\definecolor{accentblue}{HTML}{006D9C}
12\definecolor{accentorange}{HTML}{D55E00}
13\definecolor{accentteal}{HTML}{0F766E}
14\definecolor{slate}{HTML}{64748B}
15
16\newcommand{\CR}{\textsc{cr}}
17\newcommand{\NEM}{\textsc{nem}}
18\newcommand{\MER}{\textsc{mer}}
19
20\title{TeXFix-Bench: Engine-Grounded Evaluation of\\
21Single-Fault \LaTeX{} Compilation Repair}
22\author{\textbf{Prajwal~S.~Venkateshmurthy}\\[0.10em]
23\small Independent Researcher\\[0.12em]
24\small San Jose, CA, USA}
25
26\begin{document}
27\maketitle
28
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine~\cite{tan2024tex}.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
38\end{abstract}
39
40\begin{IEEEkeywords}
41automated program repair, \LaTeX{}, benchmark, compilation, large
42language models, reproducibility
43\end{IEEEkeywords}
44
45\section{Introduction}\label{sec:intro}
46\LaTeX{} compilation failures are a practical target for automated repair.
47A missing delimiter or misspelled control sequence can prevent a complete
48document from building, and the first reported diagnostic may be distant
49from the underlying fault. LLM-assisted writing systems now operate inside
50\LaTeX{} editors~\cite{wen2024overleafcopilot,hou2026paperdebugger}, but their
51publications do not provide a public, engine-pinned evaluation of
52compilation-failure repair.
53
54Program repair benchmarks pair a defect with an executable oracle and a
55fixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extends
56the contract to repository-scale issues~\cite{jimenez2024swebench}.
57TeXFix-Bench studies a narrower input-output contract: a system receives
58an existing broken source document and must return a repaired full source
59under a specified engine.
60
61\section{Benchmark Construction}\label{sec:construction}
62\begin{figure*}[t]
63\centering
64\begin{tikzpicture}[font=\footnotesize\sffamily,node distance=0.58cm,
65 phase/.style={rounded corners=2.5pt,line width=0.7pt,
66 minimum width=2.55cm,minimum height=0.82cm,align=center}]
67\node[source] (seed) {13 known-good\\seed documents};
68\node[transform,right=of seed] (mutate) {12 deterministic\\mutation operators};
69\node[engine,right=of mutate] (gate) {Tectonic 0.17.0\\quality gate};
70\node[artifact,right=of gate] (rows) {627 retained\\rows};
71\draw[flow] (seed) -- (mutate);
72\draw[flow] (mutate) -- (gate);
73\draw[flow] (gate) -- (rows);
74\end{tikzpicture}
75\caption{TeXFix-Bench data and evaluation flow. Construction is
76deterministic. Evaluation reuses saved candidates and reruns only local
77engine and PDF-text checks.}
78\label{fig:pipeline}
79\end{figure*}
80
81\section{Results}\label{sec:results}
82Table~\ref{tab:main} reports the aggregate outcome.
83Figure~\ref{fig:paired} shows \CR{} and \NEM{} for each system, and
84Figure~\ref{fig:contrasts} shows the published paired contrasts.
85
86\begin{table*}[t]
87\caption{Version 0.2 results on 86 distinct hard-track inputs. \CR{} is
88intention-to-treat. \MER{} and \NEM{} use the same denominatior.}
89\label{tab:main}
90\input{results/tables/main-results-v02.tex}
91\end{table*}
92
93Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs.
94Their normalized exact-match counts are 52, 66, and 59, respectively.
95
96\begin{thebibliography}{19}
97\bibitem{just2014defects4j}
98R. Just, D. Jalali, and M. D. Ernst, \emph{Defects4J: A database of existing
99faults to enable controlled testing studies for Java programs}, ISSTA, 2014.
100\bibitem{legoues2015manybugs}
101C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest,
102and W. Weimer, \emph{The ManyBugs and IntroClass benchmarks}, TSE, 2015.
103\bibitem{jimenez2024swebench}
104C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and
105K. Narasimhan, \emph{SWE-bench}, ICLR, 2024.
106\bibitem{chen2021codex}
107M. Chen et al., \emph{Evaluating large language models trained on code},
108arXiv:2107.03374, 2021.
109\bibitem{smith2015overfitting}
110E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, \emph{Is the cure worse
111than the disease? Overfitting in automated program repair}, FSE, 2015.
112\bibitem{demillo1978}
113R. A. DeMillo, R. J. Lipton, and F. G. Sayward, \emph{Hints on test data
114selection}, Computer, 1978.
115\bibitem{jia2011mutation}
116Y. Jia and M. Harman, \emph{An analysis and survey of the development of
117mutation testing}, TSE, 2011.
118\bibitem{gupta2017deepfix}
119R. Gupta, S. Pal, A. Kanade, and S. Shevade, \emph{DeepFix}, AAAI, 2017.
120\bibitem{yasunaga2020drrepair}
121M. Yasunaga and P. Liang, \emph{Graph-based, self-supervised program repair
122from diagnostic feedback}, ICML, 2020.
123\bibitem{zhu2022eqfix}
124F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, \emph{EqFix}, ASE, 2022.
125\bibitem{wang2024texocr}
126K. Wang et al., \emph{TexOCR-Bench: Benchmarking page-image-to-LaTeX
127reconstruction}, 2024.
128\bibitem{wen2024overleafcopilot}
129H. Wen, Z. Zhang, and Y. Li, \emph{OverleafCopilot: Empowering academic
130writing in Overleaf with large language models}, 2024.
131\bibitem{hou2026paperdebugger}
132S. Hou et al., \emph{PaperDebugger: An in-editor assistant for manuscript
133repair}, 2026.
134\bibitem{tan2024tex}
135J. Tan, K. Zhang, and X. Chen, \emph{Instrumenting TeX produced diagnostics
136for repair}, 2024.
137\bibitem{zheng2023judging}
138L. Zheng et al., \emph{Judging LLM-as-a-judge with MT-Bench and Chatbot
139Arena}, NeurIPS, 2023.
140\bibitem{panickssery2024selfpref}
141A. Panickssery, S. R. Bowman, and S. Feng, \emph{LLM evaluators recognize
142and favor their own generations}, NeurIPS, 2024.
143\bibitem{hui2024qwen}
144B. Hui et al., \emph{Qwen2.5-Coder technical report}, 2024.
145\bibitem{metaai2024llama}
146Meta AI, \emph{The Llama 3 herd of models}, 2024.
147\bibitem{kassis2024reproduce}
148E. Kassis et al., \emph{On the reproducibility of research artifacts}, 2024.
149\end{thebibliography}
150
151\end{document}
Ask AI
Key, author, or title…
chen2021codexChen, Mark et al. · 2021 · Evaluating large language models tra…
demillo1978DeMillo, Richard A. and Lipton, Richard J. and Sayward, Frederi…
gupta2017deepfixGupta, Rahul and Pal, Soham and Kanade, Aditya and Shevade…
jia2011mutationJia, Yue and Harman, Mark · 2011 · An analysis and survey of th…
smith2015overfittingSmith, Edward K. and Barr, Earl T. and Le Goues, Claire and B…
zhu2022eqfixZhu, Fengmin and Liu, Zhen and Yang, Guang and Li, Jiaxiang…
Find and add a new citation…
Add citation
DOI, arXiv id, URL, or a paper title…arXiv:2608.18329Look up
Only the identifier or title is sent, to doi.org, arXiv, or Crossref.
Paste a DOI, an arXiv id, or a URL to fetch the entry directly, or type a title to search Crossref. Try one:
arXiv: 2608.18329
DOI: 10.1145/3597503
Title: Engine-Transfer-Bench
@article{venkateshmurthy2026etb, author = {Venkateshmurthy, Prajwal S.}, title = {Engine-Transfer-Bench: An Evidence-Based Benchmark for Document Compilation Engine Selection}, journal = {arXiv preprint}, year = 2026, eprint = {2608.18329}, }
CancelAdd to .bib and cite
Added \cite{venkateshmurthy2026etb} · main.tex
main.texmain.tex (Working Tree)
CodeVisual
Working ⇆ Index
| 28 unchanged lines |
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
| 58 unchanged lines |
| 28 unchanged lines |
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine~\cite{tan2024tex}.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
| 58 unchanged lines |
1% TeXFix-Bench technical report, manuscript version 0.2.
2% Compile with: tectonic -X compile main.tex
3
4\documentclass[journal,10pt]{IEEEtran}
5\usepackage{amsmath,amssymb,booktabs,array,graphicx}
6\usepackage{xcolor,microtype,url,fontspec,newtxsf}
7\usepackage{tikz,pgfplots,balance,hyperref}
8\pgfplotsset{compat=1.18}
9\usetikzlibrary{arrows.meta,positioning,fit,backgrounds}
10
11\definecolor{accentblue}{HTML}{006D9C}
12\definecolor{accentorange}{HTML}{D55E00}
13\definecolor{accentteal}{HTML}{0F766E}
14\definecolor{slate}{HTML}{64748B}
15
16\newcommand{\CR}{\textsc{cr}}
17\newcommand{\NEM}{\textsc{nem}}
18\newcommand{\MER}{\textsc{mer}}
19
20\title{TeXFix-Bench: Engine-Grounded Evaluation of\\
21Single-Fault \LaTeX{} Compilation Repair}
22\author{\textbf{Prajwal~S.~Venkateshmurthy}\\[0.10em]
23\small Independent Researcher\\[0.12em]
24\small San Jose, CA, USA}
25
26\begin{document}
27\maketitle
28
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine~\cite{tan2024tex}.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
38\end{abstract}
39
40\begin{IEEEkeywords}
41automated program repair, \LaTeX{}, benchmark, compilation, large
42language models, reproducibility
43\end{IEEEkeywords}
44
45\section{Introduction}\label{sec:intro}
46\LaTeX{} compilation failures are a practical target for automated repair.
47A missing delimiter or misspelled control sequence can prevent a complete
48document from building, and the first reported diagnostic may be distant
49from the underlying fault. LLM-assisted writing systems now operate inside
50\LaTeX{} editors~\cite{wen2024overleafcopilot,hou2026paperdebugger}, but their
51publications do not provide a public, engine-pinned evaluation of
52compilation-failure repair.
53
54Program repair benchmarks pair a defect with an executable oracle and a
55fixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extends
56the contract to repository-scale issues~\cite{jimenez2024swebench}.
57TeXFix-Bench studies a narrower input-output contract: a system receives
58an existing broken source document and must return a repaired full source
59under a specified engine.
60
61\section{Benchmark Construction}\label{sec:construction}
62\begin{figure*}[t]
63\centering
64\begin{tikzpicture}[font=\footnotesize\sffamily,node distance=0.58cm,
65 phase/.style={rounded corners=2.5pt,line width=0.7pt,
66 minimum width=2.55cm,minimum height=0.82cm,align=center}]
67\node[source] (seed) {13 known-good\\seed documents};
68\node[transform,right=of seed] (mutate) {12 deterministic\\mutation operators};
69\node[engine,right=of mutate] (gate) {Tectonic 0.17.0\\quality gate};
70\node[artifact,right=of gate] (rows) {627 retained\\rows};
71\draw[flow] (seed) -- (mutate);
72\draw[flow] (mutate) -- (gate);
73\draw[flow] (gate) -- (rows);
74\end{tikzpicture}
75\caption{TeXFix-Bench data and evaluation flow. Construction is
76deterministic. Evaluation reuses saved candidates and reruns only local
77engine and PDF-text checks.}
78\label{fig:pipeline}
79\end{figure*}
80
81\section{Results}\label{sec:results}
82Table~\ref{tab:main} reports the aggregate outcome.
83Figure~\ref{fig:paired} shows \CR{} and \NEM{} for each system, and
84Figure~\ref{fig:contrasts} shows the published paired contrasts.
85
86\begin{table*}[t]
87\caption{Version 0.2 results on 86 distinct hard-track inputs. \CR{} is
88intention-to-treat. \MER{} and \NEM{} use the same denominatior.}
89\label{tab:main}
90\input{results/tables/main-results-v02.tex}
91\end{table*}
92
93Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs.
94Their normalized exact-match counts are 52, 66, and 59, respectively.
95
96\begin{thebibliography}{19}
97\bibitem{just2014defects4j}
98R. Just, D. Jalali, and M. D. Ernst, \emph{Defects4J: A database of existing
99faults to enable controlled testing studies for Java programs}, ISSTA, 2014.
100\bibitem{legoues2015manybugs}
101C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest,
102and W. Weimer, \emph{The ManyBugs and IntroClass benchmarks}, TSE, 2015.
103\bibitem{jimenez2024swebench}
104C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and
105K. Narasimhan, \emph{SWE-bench}, ICLR, 2024.
106\bibitem{chen2021codex}
107M. Chen et al., \emph{Evaluating large language models trained on code},
108arXiv:2107.03374, 2021.
109\bibitem{smith2015overfitting}
110E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, \emph{Is the cure worse
111than the disease? Overfitting in automated program repair}, FSE, 2015.
112\bibitem{demillo1978}
113R. A. DeMillo, R. J. Lipton, and F. G. Sayward, \emph{Hints on test data
114selection}, Computer, 1978.
115\bibitem{jia2011mutation}
116Y. Jia and M. Harman, \emph{An analysis and survey of the development of
117mutation testing}, TSE, 2011.
118\bibitem{gupta2017deepfix}
119R. Gupta, S. Pal, A. Kanade, and S. Shevade, \emph{DeepFix}, AAAI, 2017.
120\bibitem{yasunaga2020drrepair}
121M. Yasunaga and P. Liang, \emph{Graph-based, self-supervised program repair
122from diagnostic feedback}, ICML, 2020.
123\bibitem{zhu2022eqfix}
124F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, \emph{EqFix}, ASE, 2022.
125\bibitem{wang2024texocr}
126K. Wang et al., \emph{TexOCR-Bench: Benchmarking page-image-to-LaTeX
127reconstruction}, 2024.
128\bibitem{wen2024overleafcopilot}
129H. Wen, Z. Zhang, and Y. Li, \emph{OverleafCopilot: Empowering academic
130writing in Overleaf with large language models}, 2024.
131\bibitem{hou2026paperdebugger}
132S. Hou et al., \emph{PaperDebugger: An in-editor assistant for manuscript
133repair}, 2026.
134\bibitem{tan2024tex}
135J. Tan, K. Zhang, and X. Chen, \emph{Instrumenting TeX produced diagnostics
136for repair}, 2024.
137\bibitem{zheng2023judging}
138L. Zheng et al., \emph{Judging LLM-as-a-judge with MT-Bench and Chatbot
139Arena}, NeurIPS, 2023.
140\bibitem{panickssery2024selfpref}
141A. Panickssery, S. R. Bowman, and S. Feng, \emph{LLM evaluators recognize
142and favor their own generations}, NeurIPS, 2024.
143\bibitem{hui2024qwen}
144B. Hui et al., \emph{Qwen2.5-Coder technical report}, 2024.
145\bibitem{metaai2024llama}
146Meta AI, \emph{The Llama 3 herd of models}, 2024.
147\bibitem{kassis2024reproduce}
148E. Kassis et al., \emph{On the reproducibility of research artifacts}, 2024.
149\end{thebibliography}
150
151\end{document}
Versioning
One version per successful compile that changed the source.Source only
V6
Restore
LaTeX (latexmk) · main.tex
9/13/2026, 4:57:36 PM
7 files · 183.8 KB · ded1c2ae
V5
RestoreOverwrite allCancel
LaTeX (latexmk) · main.tex
9/13/2026, 3:52:03 PM
7 files · 183.8 KB · 157c1ffb
V4
Restore
LaTeX (latexmk) · main.tex
9/6/2026, 4:22:40 PM
7 files · 183.7 KB · 891b7ee7
Advanced
Search 16 projects by name, ID, main file, color, or export
Advanced filters
ResetFilters apply to the project shelf immediately
MARKDOWNAlpine eDNA Pilot — Lab Notebook
DocumentUpdated Jul 31
TECTONICMapping Pollinator Corridors — Research Poster
DocumentUpdated Jul 29
TECTONICFederated Learning Data Flow
ImageUpdated Jul 29
TECTONICCatalyst Screening Data Report
DocumentUpdated Jul 29
TECTONICMangrove Canopy Drone Survey
DocumentUpdated Jul 28
Alex Chen
Senior Software Engineer
[email protected] · (650) 555-0142 · Mountain View, CA · alexchen.dev · github.com/alexchen
SUMMARY
Senior Software Engineer (L5) with 9+ years designing and operating large-scale distributed systems. Deep experience in backend infrastructure, performance, and reliability.
EXPERIENCE
Senior Software Engineer (L5)Google
Mountain View, CAMar 2020 — Present
- Tech lead for a Search serving component handling 2M+ queries/second; cut p99 latency 38%.
- Designed a globally replicated feature store on Spanner backing 40+ ML models.
- Led migration of a 300-service fleet to a new RPC framework; reduced on-call pages 45%.
- Mentored six engineers and ran the team’s design-review program.
Software Engineer (L4)Google
Mountain View, CAJul 2017 — Mar 2020
- Built a real-time aggregation pipeline processing 8B events/day.
- Cut batch-job cost 30% with sharding and incremental computation.
Software EngineerStripe
San Francisco, CAAug 2015 — Jun 2017
- Shipped ledger and reconciliation services processing $60B+/year.
- Reduced a reconciliation run from six hours to 25 minutes.
SELECTED PROJECTS
Ratelgithub.com/alexchen/ratel
Go, Raft, gRPC — distributed rate limiter doing 4M+ decisions/sec/node.
tqlgithub.com/alexchen/tql
Rust — typed query builder for Postgres with compile-time-checked SQL.
EDUCATION
M.S. Computer ScienceStanford University
B.S. Computer ScienceUniversity of Illinois Urbana-Champaign
SKILLS
Languages: C++, Go, Rust, Python, Java, SQL
Systems: Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis
TECTONICSleep and Memory Consolidation — Evidence Map
DocumentUpdated Jul 28
TECTONICUrban Heat Transect Field Protocol
DocumentUpdated Jul 27
TECTONICNSF Progress Report — Year 2
DocumentUpdated Jul 27
TYPSTArjun Rao — Computational Linguistics CV
DocumentUpdated Jul 11
TECTONICOrganoid Response Profiles for Therapy Selection
DocumentUpdated Jul 11
TECTONICSTAT 214 — Causal Inference Problem Set
DocumentUpdated Mar 3
TECTONICDextrous Manipulation — Proposal
DocumentUpdated Jul 9
TECTONICCivic Shade and Pedestrian Heat Exposure
DocumentUpdated Jul 8
TECTONICCS 271 — Approximation Algorithms PS3
DocumentUpdated Jul 5
TECTONICWeak-Lensing Mass Reconstruction of NCJ 1427
DocumentUpdated Jul 2
TECTONICStatistical Consulting Report
DocumentUpdated Jun 25
Choose how this manuscript begins. Every part of it stays yours to change.
Research project
A study folder with sections, sources and review notes, and a first task that frames the question.
Import a project
Continue a manuscript you already have: an archive, a Word or Markdown draft, or a GitHub repository.
Use a template
Begin from a prepared layout for a journal article, thesis, report, poster or talk.
Search templates
All engines
ATS-friendly
Offline
Jane Doe
Data Scientist
[email protected] · New York, NY · janedoe.dev · github.com/janedoe
SUMMARY
Data scientist focused on trustworthy machine learning, experimentation, and decision systems used by product and research teams.
EXPERIENCE
Senior Data ScientistAnthropic
New York, NY2021 — Present
- Built evaluation systems for large language models across safety and product quality.
- Designed experiments used to guide high-impact model launches.
Machine Learning EngineerAirbnb
San Francisco, CA2018 — 2021
- Developed ranking models and reliable offline evaluation pipelines.
- Partnered with product teams to improve marketplace search quality.
Data AnalystSpotify
New York, NY2016 — 2018
- Created retention models and executive experimentation dashboards.
SELECTED PROJECTS
Model Cardsjanedoe.dev/model-cards
Open evaluation templates for production ML systems.
CausalKitgithub.com/janedoe/causalkit
Python package for reproducible causal inference workflows.
EDUCATION
M.S. StatisticsColumbia University
B.S. MathematicsUniversity of Michigan
SKILLS
Languages: Python, R, SQL, PyTorch, JAX
Systems: Spark, dbt, BigQuery, Airflow, MLflow, Kubernetes
Untitled
Untitled
Untitled Markdown Document
InputEncoderClassifier
Jane Doe
Data Scientist
[email protected] · New York, NY · janedoe.dev · github.com/janedoe
SUMMARY
Data scientist focused on trustworthy machine learning, experimentation, and decision systems used by product and research teams.
EXPERIENCE
Senior Data ScientistAnthropic
New York, NY2021 — Present
- Built evaluation systems for large language models across safety and product quality.
- Designed experiments used to guide high-impact model launches.
Machine Learning EngineerAirbnb
San Francisco, CA2018 — 2021
- Developed ranking models and reliable offline evaluation pipelines.
- Partnered with product teams to improve marketplace search quality.
Data AnalystSpotify
New York, NY2016 — 2018
- Created retention models and executive experimentation dashboards.
SELECTED PROJECTS
Model Cardsjanedoe.dev/model-cards
Open evaluation templates for production ML systems.
CausalKitgithub.com/janedoe/causalkit
Python package for reproducible causal inference workflows.
EDUCATION
M.S. StatisticsColumbia University
B.S. MathematicsUniversity of Michigan
SKILLS
Languages: Python, R, SQL, PyTorch, JAX
Systems: Spark, dbt, BigQuery, Airflow, MLflow, Kubernetes
Alex Chen
Senior Software Engineer
[email protected] · (650) 555-0142 · Mountain View, CA · alexchen.dev · github.com/alexchen
SUMMARY
Senior Software Engineer (L5) with 9+ years designing and operating large-scale distributed systems. Deep experience in backend infrastructure, performance, and reliability.
EXPERIENCE
Senior Software Engineer (L5)Google
Mountain View, CAMar 2020 — Present
- Tech lead for a Search serving component handling 2M+ queries/second; cut p99 latency 38%.
- Designed a globally replicated feature store on Spanner backing 40+ ML models.
- Led migration of a 300-service fleet to a new RPC framework; reduced on-call pages 45%.
- Mentored six engineers and ran the team’s design-review program.
Software Engineer (L4)Google
Mountain View, CAJul 2017 — Mar 2020
- Built a real-time aggregation pipeline processing 8B events/day.
- Cut batch-job cost 30% with sharding and incremental computation.
Software EngineerStripe
San Francisco, CAAug 2015 — Jun 2017
- Shipped ledger and reconciliation services processing $60B+/year.
- Reduced a reconciliation run from six hours to 25 minutes.
SELECTED PROJECTS
Ratelgithub.com/alexchen/ratel
Go, Raft, gRPC — distributed rate limiter doing 4M+ decisions/sec/node.
tqlgithub.com/alexchen/tql
Rust — typed query builder for Postgres with compile-time-checked SQL.
EDUCATION
M.S. Computer ScienceStanford University
B.S. Computer ScienceUniversity of Illinois Urbana-Champaign
SKILLS
Languages: C++, Go, Rust, Python, Java, SQL
Systems: Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis
Morgan Lee
Product Engineer
[email protected] · Brooklyn, NY · morganlee.design · github.com/morganlee
SUMMARY
Product engineer bridging design systems and frontend infrastructure to build accessible, high-craft tools for creative teams.
EXPERIENCE
Staff Product EngineerFigma
New York, NY2022 — Present
- Led architecture for collaborative prototyping workflows used by millions.
- Created an accessible component platform shared across six product teams.
Senior Frontend EngineerNotion
San Francisco, CA2019 — 2022
- Shipped core editor interactions and improved canvas rendering performance 42%.
- Partnered with design to establish product-wide interaction standards.
Interaction DesignerIDEO
Chicago, IL2016 — 2019
- Prototyped service experiences for health and education clients.
SELECTED PROJECTS
Prismmorganlee.design/prism
Open-source accessible color and typography toolkit.
Local First UIgithub.com/morganlee/lfui
Patterns for resilient collaborative interfaces.
EDUCATION
M.Des. Interaction DesignCarnegie Mellon University
B.S. Computer ScienceNorthwestern University
SKILLS
Languages: TypeScript, React, Rust, Swift, Figma
Systems: WebGL, Canvas, design systems, accessibility, prototyping
Setup
Modern ResumeTECTONICneeds setup
Morgan Lee
Product Engineer
[email protected] · Brooklyn, NY · morganlee.design · github.com/morganlee
SUMMARY
Product engineer bridging design systems and frontend infrastructure to build accessible, high-craft tools for creative teams.
EXPERIENCE
Staff Product EngineerFigma
New York, NY2022 — Present
- Led architecture for collaborative prototyping workflows used by millions.
- Created an accessible component platform shared across six product teams.
Senior Frontend EngineerNotion
San Francisco, CA2019 — 2022
- Shipped core editor interactions and improved canvas rendering performance 42%.
- Partnered with design to establish product-wide interaction standards.
Interaction DesignerIDEO
Chicago, IL2016 — 2019
- Prototyped service experiences for health and education clients.
SELECTED PROJECTS
Prismmorganlee.design/prism
Open-source accessible color and typography toolkit.
Local First UIgithub.com/morganlee/lfui
Patterns for resilient collaborative interfaces.
EDUCATION
M.Des. Interaction DesignCarnegie Mellon University
B.S. Computer ScienceNorthwestern University
SKILLS
Languages: TypeScript, React, Rust, Swift, Figma
Systems: WebGL, Canvas, design systems, accessibility, prototyping
Alex Chen
Research Engineer
[email protected] · Berlin, Germany · alexchen.dev
SUMMARY
Research engineer building fast, expressive systems for scientific communication and reproducible technical publishing.
EXPERIENCE
Research EngineerTypst
Berlin, Germany2022 — Present
- Built incremental layout and diagnostics for a modern typesetting engine.
- Improved large-document render latency and editor feedback loops.
Software EngineerMozilla
Remote2019 — 2022
- Worked on text shaping, browser layout, and developer tooling.
Research AssistantTU Berlin
Berlin, Germany2017 — 2019
- Published work on interactive document systems.
SELECTED PROJECTS
Inkstonegithub.com/alexchen/inkstone
A small language server for technical documents.
Glyphalexchen.dev/glyph
Experiments in high-performance text layout.
EDUCATION
M.Sc. Computer ScienceTU Berlin
B.Sc. Computer ScienceUniversity of Edinburgh
SKILLS
Languages: Rust, C++, TypeScript, Python
Systems: Compilers, text layout, language servers, WebAssembly
Software Engineer Resume
Lilac
Back
OleaflyAlex Chen - Google Resume
main.tex
CodeVisual
1
\documentclass[11pt,letterpaper]{article}2
\usepackage[T1]{fontenc}3
\usepackage[margin=0.5in]{geometry}4
\usepackage{titlesec}5
\usepackage{enumitem}6
\usepackage{hyperref}7
8
% ATS-friendly: single column, real selectable text, no tables-for-layout,9
% embedded subset fonts. Linear reading order so parsers extract cleanly.10
\setlength{\parindent}{0pt}11
\pagenumbering{gobble}12
\hypersetup{colorlinks=true, urlcolor=black, linkcolor=black}13
14
\titleformat{\section}{\large\bfseries\uppercase}{}{0em}{}[\vspace{2pt}\titlerule]15
\titlespacing*{\section}{0pt}{8pt}{4pt}16
\setlist[itemize]{leftmargin=14pt, itemsep=1pt, topsep=2pt, parsep=0pt}17
18
% role{Title}{Company}{Location}{Dates}19
\newcommand{\role}[4]{%20
\textbf{#1} \hfill #2 \\21
\textit{#3} \hfill \textit{#4}%22
}23
24
\begin{document}25
26
\begin{center}27
{\Huge \textbf{Alex Chen}}\\[3pt]28
\small29
Senior Software Engineer\\[2pt]30
\href{mailto:[email protected]}{[email protected]}\,$\cdot$\,31
(650) 555-0142\,$\cdot$\,32
Mountain View, CA\,$\cdot$\,33
\href{https://alexchen.dev}{alexchen.dev}\,$\cdot$\,34
\href{https://github.com/alexchen}{github.com/alexchen}\,$\cdot$\,35
\href{https://linkedin.com/in/alexchen}{linkedin.com/in/alexchen}36
\end{center}37
\vspace{2pt}38
39
\section*{Summary}40
Senior Software Engineer (L5) with 9+ years designing and operating large-scale41
distributed systems. Deep experience in backend infrastructure, performance, and42
reliability, with a track record of shipping products used by hundreds of43
millions of users and mentoring engineers toward senior roles.44
45
\section*{Experience}46
\role{Senior Software Engineer (L5)}{Google}{Mountain View, CA}{Mar 2020 -- Present}47
\begin{itemize}48
\item Tech lead for a Search serving component handling 2M+ queries/second; drove a redesign that cut p99 latency 38\% and saved an estimated \$14M/year in compute.49
\item Designed and launched a globally-replicated feature store on Spanner backing 40+ ML models, adopted by 12 teams across Search and Ads.50
\item Led migration of a 300-service fleet to a new RPC framework, improving tail latency and reducing on-call pages by 45\%.51
\item Mentored 6 engineers (2 promoted to senior); ran the team's design-review and readability programs.52
\end{itemize}53
\vspace{3pt}54
\role{Software Engineer (L4)}{Google}{Mountain View, CA}{Jul 2017 -- Mar 2020}55
\begin{itemize}56
\item Built a real-time aggregation pipeline (C++, Flume) processing 8B events/day for a Search-quality dashboard used org-wide.57
\item Cut batch-job cost 30\% by reworking sharding and introducing incremental recomputation.58
\end{itemize}59
\vspace{3pt}60
\role{Software Engineer}{Stripe}{San Francisco, CA}{Aug 2015 -- Jun 2017}61
\begin{itemize}62
\item Shipped core ledger and reconciliation services for a payments platform processing \$60B+/year.63
\item Reduced a reconciliation run from 6 hours to 25 minutes via parallelization and a columnar store.64
\end{itemize}65
66
\section*{Selected Projects}67
\textbf{Ratel} \hfill \href{https://github.com/alexchen/ratel}{github.com/alexchen/ratel} \\68
\textit{Go, Raft, gRPC} --- open-source distributed rate limiter doing 4M+ decisions/sec/node; 1.5k GitHub stars.\par\vspace{4pt}69
\textbf{tql} \hfill \href{https://github.com/alexchen/tql}{github.com/alexchen/tql} \\70
\textit{Rust} --- a typed query builder for Postgres with compile-time-checked SQL.71
72
\section*{Education}73
\textbf{M.S. Computer Science} \hfill Stanford University \\74
\textit{2013 -- 2015} \hfill \textit{Focus: Distributed Systems}\par\vspace{4pt}75
\textbf{B.S. Computer Science} \hfill University of Illinois Urbana-Champaign \\76
\textit{2009 -- 2013} \hfill \textit{GPA: 3.9 / 4.0}77
78
\section*{Skills}79
\textbf{Languages:} C++, Go, Rust, Python, Java, SQL \\80
\textbf{Systems:} Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis \\81
\textbf{Focus:} Distributed systems, performance, reliability (SLOs), system design, mentoring82
83
\end{document}Logs1.1s100%⌃ 1 of 1 ⌄
Compiling1/3 done
1 running · 1 queued
Language analysisCurrent project revision analyzed
DONECompilingProducing and verifying PDF output
RUNNINGRendering PDFWaiting for verified compile output
QUEUEDAlex Chen
Senior Software Engineer
[email protected] · (650) 555-0142 · Mountain View, CA · alexchen.dev · github.com/alexchen
SUMMARY
Senior Software Engineer (L5) with 9+ years designing and operating large-scale distributed systems. Deep experience in backend infrastructure, performance, and reliability.
EXPERIENCE
Senior Software Engineer (L5)Google
Mountain View, CAMar 2020 — Present
- Tech lead for a Search serving component handling 2M+ queries/second; cut p99 latency 38%.
- Designed a globally replicated feature store on Spanner backing 40+ ML models.
- Led migration of a 300-service fleet to a new RPC framework; reduced on-call pages 45%.
- Mentored six engineers and ran the team’s design-review program.
Software Engineer (L4)Google
Mountain View, CAJul 2017 — Mar 2020
- Built a real-time aggregation pipeline processing 8B events/day.
- Cut batch-job cost 30% with sharding and incremental computation.
Software EngineerStripe
San Francisco, CAAug 2015 — Jun 2017
- Shipped ledger and reconciliation services processing $60B+/year.
- Reduced a reconciliation run from six hours to 25 minutes.
SELECTED PROJECTS
Ratelgithub.com/alexchen/ratel
Go, Raft, gRPC — distributed rate limiter doing 4M+ decisions/sec/node.
tqlgithub.com/alexchen/tql
Rust — typed query builder for Postgres with compile-time-checked SQL.
EDUCATION
M.S. Computer ScienceStanford University
B.S. Computer ScienceUniversity of Illinois Urbana-Champaign
SKILLS
Languages: C++, Go, Rust, Python, Java, SQL
Systems: Spanner, Bigtable, Kubernetes, Kafka, gRPC / Protobuf, Redis
main.tex
CodeVisual
Results
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 just2014defects4j.
TABLE I
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Evaluation method
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion.
CR = compile(c) ∧ LCStok(Tc, Tr) ≥ 0.80
Discussion and limitations
These results show why compilation and edit precision should be reported together, but they do not establish a universal model ranking jimenez2024swebench.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice.
Conclusion
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
1% TeXFix-Bench technical report, manuscript version 0.2.
2% Compile with: tectonic -X compile main.tex
3
4\documentclass[journal,10pt]{IEEEtran}
5\usepackage{amsmath,amssymb,booktabs,array,graphicx}
6\usepackage{xcolor,microtype,url,fontspec,newtxsf}
7\usepackage{tikz,pgfplots,balance,hyperref}
8\pgfplotsset{compat=1.18}
9\usetikzlibrary{arrows.meta,positioning,fit,backgrounds}
10
11\definecolor{accentblue}{HTML}{006D9C}
12\definecolor{accentorange}{HTML}{D55E00}
13\definecolor{accentteal}{HTML}{0F766E}
14\definecolor{slate}{HTML}{64748B}
15
16\newcommand{\CR}{\textsc{cr}}
17\newcommand{\NEM}{\textsc{nem}}
18\newcommand{\MER}{\textsc{mer}}
19
20\title{TeXFix-Bench: Engine-Grounded Evaluation of\\
21Single-Fault \LaTeX{} Compilation Repair}
22\author{\textbf{Prajwal~S.~Venkateshmurthy}\\[0.10em]
23\small Independent Researcher\\[0.12em]
24\small San Jose, CA, USA}
25
26\begin{document}
27\maketitle
28
29\begin{abstract}
30Compilation repair for \LaTeX{} is easy to score badly. A candidate may
31compile after deleting or hiding content, while exact source equality
32rejects valid alternative repairs. We present TeXFix-Bench, a controlled
33benchmark for repairing complete, broken \LaTeX{} sources under a pinned engine~\cite{tan2024tex}.
34The generator applies 12 deterministic single-fault operators to 13
35hand-authored seed documents. It retains 627 engine-validated rows,
36comprising 300 unique hard-track inputs and 67 unique warning-only
37inputs after hash deduplication.
38\end{abstract}
39
40\begin{IEEEkeywords}
41automated program repair, \LaTeX{}, benchmark, compilation, large
42language models, reproducibility
43\end{IEEEkeywords}
44
45\section{Introduction}\label{sec:intro}
46\LaTeX{} compilation failures are a practical target for automated repair.
47A missing delimiter or misspelled control sequence can prevent a complete
48document from building, and the first reported diagnostic may be distant
49from the underlying fault. LLM-assisted writing systems now operate inside
50\LaTeX{} editors~\cite{wen2024overleafcopilot,hou2026paperdebugger}, but their
51publications do not provide a public, engine-pinned evaluation of
52compilation-failure repair.
53
54Program repair benchmarks pair a defect with an executable oracle and a
55fixed harness~\cite{just2014defects4j,legoues2015manybug}. SWE-bench extends
56the contract to repository-scale issues~\cite{jimenez2024swebench}.
57TeXFix-Bench studies a narrower input-output contract: a system receives
58an existing broken source document and must return a repaired full source
59under a specified engine.
60
61\section{Benchmark Construction}\label{sec:construction}
62\begin{figure*}[t]
63\centering
64\begin{tikzpicture}[font=\footnotesize\sffamily,node distance=0.58cm,
65 phase/.style={rounded corners=2.5pt,line width=0.7pt,
66 minimum width=2.55cm,minimum height=0.82cm,align=center}]
67\node[source] (seed) {13 known-good\\seed documents};
68\node[transform,right=of seed] (mutate) {12 deterministic\\mutation operators};
69\node[engine,right=of mutate] (gate) {Tectonic 0.17.0\\quality gate};
70\node[artifact,right=of gate] (rows) {627 retained\\rows};
71\draw[flow] (seed) -- (mutate);
72\draw[flow] (mutate) -- (gate);
73\draw[flow] (gate) -- (rows);
74\end{tikzpicture}
75\caption{TeXFix-Bench data and evaluation flow. Construction is
76deterministic. Evaluation reuses saved candidates and reruns only local
77engine and PDF-text checks.}
78\label{fig:pipeline}
79\end{figure*}
80
81\section{Results}\label{sec:results}
82Table~\ref{tab:main} reports the aggregate outcome.
83Figure~\ref{fig:paired} shows \CR{} and \NEM{} for each system, and
84Figure~\ref{fig:contrasts} shows the published paired contrasts.
85
86\begin{table*}[t]
87\caption{Version 0.2 results on 86 distinct hard-track inputs. \CR{} is
88intention-to-treat. \MER{} and \NEM{} use the same denominatior.}
89\label{tab:main}
90\input{results/tables/main-results-v02.tex}
91\end{table*}
92
93Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs.
94Their normalized exact-match counts are 52, 66, and 59, respectively.
95
96\begin{thebibliography}{19}
97\bibitem{just2014defects4j}
98R. Just, D. Jalali, and M. D. Ernst, \emph{Defects4J: A database of existing
99faults to enable controlled testing studies for Java programs}, ISSTA, 2014.
100\bibitem{legoues2015manybugs}
101C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest,
102and W. Weimer, \emph{The ManyBugs and IntroClass benchmarks}, TSE, 2015.
103\bibitem{jimenez2024swebench}
104C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and
105K. Narasimhan, \emph{SWE-bench}, ICLR, 2024.
106\bibitem{chen2021codex}
107M. Chen et al., \emph{Evaluating large language models trained on code},
108arXiv:2107.03374, 2021.
109\bibitem{smith2015overfitting}
110E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, \emph{Is the cure worse
111than the disease? Overfitting in automated program repair}, FSE, 2015.
112\bibitem{demillo1978}
113R. A. DeMillo, R. J. Lipton, and F. G. Sayward, \emph{Hints on test data
114selection}, Computer, 1978.
115\bibitem{jia2011mutation}
116Y. Jia and M. Harman, \emph{An analysis and survey of the development of
117mutation testing}, TSE, 2011.
118\bibitem{gupta2017deepfix}
119R. Gupta, S. Pal, A. Kanade, and S. Shevade, \emph{DeepFix}, AAAI, 2017.
120\bibitem{yasunaga2020drrepair}
121M. Yasunaga and P. Liang, \emph{Graph-based, self-supervised program repair
122from diagnostic feedback}, ICML, 2020.
123\bibitem{zhu2022eqfix}
124F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, \emph{EqFix}, ASE, 2022.
125\bibitem{wang2024texocr}
126K. Wang et al., \emph{TexOCR-Bench: Benchmarking page-image-to-LaTeX
127reconstruction}, 2024.
128\bibitem{wen2024overleafcopilot}
129H. Wen, Z. Zhang, and Y. Li, \emph{OverleafCopilot: Empowering academic
130writing in Overleaf with large language models}, 2024.
131\bibitem{hou2026paperdebugger}
132S. Hou et al., \emph{PaperDebugger: An in-editor assistant for manuscript
133repair}, 2026.
134\bibitem{tan2024tex}
135J. Tan, K. Zhang, and X. Chen, \emph{Instrumenting TeX produced diagnostics
136for repair}, 2024.
137\bibitem{zheng2023judging}
138L. Zheng et al., \emph{Judging LLM-as-a-judge with MT-Bench and Chatbot
139Arena}, NeurIPS, 2023.
140\bibitem{panickssery2024selfpref}
141A. Panickssery, S. R. Bowman, and S. Feng, \emph{LLM evaluators recognize
142and favor their own generations}, NeurIPS, 2024.
143\bibitem{hui2024qwen}
144B. Hui et al., \emph{Qwen2.5-Coder technical report}, 2024.
145\bibitem{metaai2024llama}
146Meta AI, \emph{The Llama 3 herd of models}, 2024.
147\bibitem{kassis2024reproduce}
148E. Kassis et al., \emph{On the reproducibility of research artifacts}, 2024.
149\end{thebibliography}
150
151\end{document}
Logs
1.9s
100%
1
of 2
Compiling
1/3 done
1 running · 1 queued
- Language analysisCurrent project revision analyzed
- CompilingProducing and verifying PDF output
- Rendering PDFWaiting for verified compile output
TeXFix-Bench: Engine-Grounded Evaluation of
Single-Fault LATEX Compilation Repair
Single-Fault LATEX Compilation Repair
Prajwal S. Venkateshmurthy
Independent Researcher
San Jose, CA, USA
Independent Researcher
San Jose, CA, USA
Abstract—Compilation repair for LaTeX is easy to score badly. A candidate may compile after deleting or hiding content, while exact source equality rejects valid alternative repairs. We present TeXFix-Bench, a controlled benchmark for repairing complete, broken LaTeX sources under a pinned engine. The generator applies 12 deterministic single-fault operators to 13 hand-authored seed documents. It retains 627 engine-validated rows, comprising 300 unique hard-track inputs and 67 unique warning-only inputs after hash deduplication.
Index Terms—automated program repair, LaTeX, benchmark, compilation, large language models, reproducibility
I. INTRODUCTION
LaTeX compilation failures are a practical target for automated repair. A missing delimiter or misspelled control sequence can prevent a complete document from building, and the first reported diagnostic may be distant from the underlying fault. LLM-assisted writing systems now operate inside LaTeX editors , but their publications do not provide a public, engine-pinned evaluation of compilation-failure repair.
Program repair benchmarks pair a defect with an executable oracle and a fixed harness . TeXFix-Bench studies a narrower contract: a broken source document in, a repaired full source out, under a specified engine.
II. RELATED WORK
TexOCR-Bench evaluates page-image-to-LaTeX reconstruction , and EqFix repairs errors in individual equations by synthesizing rules from examples . Overfitting to a weak oracle is a known hazard .
III. TASK AND SCOPE
A system receives one broken source file and returns one repaired source file. The engine, its version, and the build command are fixed for every attempt.
CR = compile(c) ∧ LCStok(Tc, Tr) ≥ 0.80(1)
IV. BENCHMARK CONSTRUCTION
Fig. 1. TeXFix-Bench data and evaluation flow. Construction is deterministic.
Every generated row passes an engine gate before it is retained, and duplicate broken sources are removed by SHA-256 so that no input is scored twice .
V. EVALUATION METHOD
Compile Recovery requires a successful Tectonic 0.17.0 run and at least 0.80 token-level LCS similarity between text extracted from the candidate and reference PDFs. Normalized exact match sits beside it, because compilation alone cannot separate a faithful repair from a deletion .
TABLE I
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
Version 0.2 results on 86 distinct hard-track inputs. CR is intention-to-treat.
| System | CR | CR % | NEM | Fail |
| Identity | 0/86 | 0.0 | 0/86 | 0 |
| Rule | 34/86 | 39.5 | 28/86 | 0 |
| Qwen-7B + fb | 57/86 | 66.3 | 17/86 | 0 |
| MiniMax M3 | 75/86 | 87.2 | 50/86 | 2 |
| DeepSeek V4 | 81/86 | 94.2 | 38/86 | 2 |
| Gemini 3.5 | 82/86 | 95.3 | 26/86 | 0 |
| Claude S5 | 85/86 | 98.8 | 52/86 | 0 |
| GPT-5.6 Sol | 85/86 | 98.8 | 66/86 | 1 |
| Grok 4.5 | 85/86 | 98.8 | 59/86 | 0 |
Fig. 2. Compile Recovery and normalized exact match on the fixed cohort of n = 86 hard-track inputs. Circles denote CR, squares NEM.
VI. RESULTS
Claude Sonnet 5, GPT-5.6 Sol, and Grok 4.5 each recover 85 of 86 inputs, yet their normalized exact-match counts are 52, 66, and 59 . Compilation and edit precision must be reported together.
VII. CONCLUSION
The contribution is an auditable task definition, an executable oracle, a fixed cohort, and a replayable candidate ledger.
REFERENCES
[1]R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A database of existing faults to enable controlled testing studies for Java programs,” in Proc. ISSTA, 2014, pp. 437–440.
[2]C. Le Goues, N. Holtschulte, E. K. Smith, Y. Brun, P. Devanbu, S. Forrest, and W. Weimer, “The ManyBugs and IntroClass benchmarks for automated repair of C programs,” IEEE Trans. Softw. Eng., vol. 41, no. 12, pp. 1236–1256, 2015.
[3]C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, “SWE-bench: Can language models resolve real-world GitHub issues?” in Proc. ICLR, 2024.
[4]M. Chen et al., “Evaluating large language models trained on code,” arXiv:2107.03374, 2021.
[5]E. K. Smith, E. T. Barr, C. Le Goues, and Y. Brun, “Is the cure worse than the disease? Overfitting in automated program repair,” in Proc. ESEC/FSE, 2015, pp. 532–543.
[6]R. A. DeMillo, R. J. Lipton, and F. G. Sayward, “Hints on test data selection: Help for the practicing programmer,” Computer, vol. 11, no. 4, pp. 34–41, 1978.
[7]Y. Jia and M. Harman, “An analysis and survey of the development of mutation testing,” IEEE Trans. Softw. Eng., vol. 37, no. 5, pp. 649–678, 2011.
[8]R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing common C language errors by deep learning,” in Proc. AAAI, vol. 31, no. 1, pp. 1345–1351, 2017.
[9]M. Yasunaga and P. Liang, “Graph-based, self-supervised program repair from diagnostic feedback,” in Proc. ICML, PMLR, vol. 119, pp. 10799–10808, 2020.
[10]F. Zhu, Z. Liu, G. Yang, J. Li, and S. Cheung, “EqFix: Fixing LaTeX equation errors by examples,” in SETTA 2022, LNCS 13649, pp. 89–109.
[11]K. Wang et al., “TexOCR-Bench: Benchmarking page-image-to-LaTeX reconstruction,” in Proc. 64th ACL, Vol. 1, 2026.
[12]H. Wen, Z. Zhang, and Y. Li, “OverleafCopilot: Empowering academic writing in Overleaf with large language models,” arXiv:2403.09733, 2024.
[13]S. Hou et al., “PaperDebugger: Assisting scientific writing, review, and editing,” in Companion Proc. ACM Web Conf., 2026.
[14]J. Tan, K. Zhang, and X. Chen, “Inconsistencies in TeX-produced documents,” in Proc. ISSTA, 2024.
[15]L. Zheng et al., “Judging LLM-as-a-judge with MT-Bench and Chatbot Arena,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 46595–46623, 2023.
[16]A. Panickssery, S. R. Bowman, and S. Feng, “LLM evaluators recognize and favor their own generations,” Adv. Neural Inf. Process. Syst., vol. 37, 2024.
[17]B. Hui et al., “Qwen2.5-Coder technical report,” arXiv:2409.12186, 2024.
[18]Meta AI, “Llama 3.2 model card,” 2024.
[19]E. Kassis et al., “Agent skills for reproducible research agents,” arXiv:2609.00065, 2026.
Zoom in
Zoom out
Fit to width
Fit to height
Reset to 100%
25%
50%
75%
100%
150%
200%
400%
Rename tab:main
tab:main
2 edits across 1 file
CancelRename
Project info
main.tex · 7 files
Document
Words1,284
In text1,160
In headers44
Outside text80
Headers7
Figures2
Math inline6
Math displayed1
Characters8,946
Lines95
Proofreading · main.tex
Issues7
Spelling3
Grammar & style4
Renamed to "tab:main-results" (2 edits in 1 file)
Exported main.pdf
منظومة بحثية قوية
من أول استشهاد إلى ملف PDF النهائي.
سوّد، وجمّع، ودقّق، وابحث، واستشهد، وراجع، وانشر دون تركيب أدوات متفرقة. يحتفظ Oleafly بمصدرك ومعاينتك ومراجعك والذكاء الاصطناعي وسجل Git في مساحة عمل واحدة تتحكم فيها أنت.
paper.pdfmain.texlocal ✓
استيراد ما لديك
أعد بناء العديد من ملفات PDF المستندة إلى النصوص إلى LaTeX قابل للتحرير محليًا، أو حوّل DOCX عبر Pandoc مُدار، أو دع نموذج رؤية يحوّل صورة صفحة إلى نص. مع تحسين اختياري بالذكاء الاصطناعي بعد ذلك.
main.tex→PDFDOCXHTML
صدِّر إلى وجهتك
صدّر PDF وDOCX وHTML وMarkdown وغيرها من القوائم السياقية. ويمكنك أيضًا تنزيل المشروع كاملًا كملف ZIP للمصدر.
-- NORMAL --:wq
accent · themes · layouts
اجعلها لك
وضع Vim، وسمات فاتحة وداكنة، وألوان تمييز، وسبعة إعدادات تخطيط مسبقة، واختصارات لوحة مفاتيح قابلة للتعديل. يجب أن يناسب المحرر يديك.
CodeVisual
\section{Results}
We find that \textbf{local-first}
editing \emph{wins} in every
benchmark we ran.
3 Results
We find that local-first editing wins in every benchmark we ran.
unsupported LaTeX stays visible, never dropped
اكتب بوضع الكود أو بالوضع المرئي
قم بقلب أي مستند LaTeX أو Markdown إلى محرر مرئي: العناوين، والقوائم، والخط العريض، والروابط، التي تم تحريرها مباشرة، مع التراجع المنسق عبر كلا الوضعين. تظل الأوامر غير المدعومة مرئية ككتل خام بدلاً من إسقاطها بصمت، وبالتالي فإن رحلة العودة إلى المصدر غير مدمرة.
main.tex
\section{Results}
We evaluate on
\cite{gatto24}
PDF
SyncTeX، على مستوى الكلمة
انقر مع ⌘ على كلمة في ملف PDF لتنتقل إلى الكلمة نفسها بالضبط في المصدر. وارجع باستخدام ⌘⇧J.
F2 · rename symbol
intro.tex \ref{fig:pipelinefig:pipelinefig:arch}
results.tex \ref{fig:pipelinefig:pipelinefig:arch}
ذكاء الكود
انتقل إلى التعريف، وابحث عن المراجع، وأعد تسمية التسمية، أو مفتاح الاقتباس، أو الماكرو عبر كل ملف.
…shown in Figure 3. /fig
/figure
/table
/cite
أوامر الشرطة المائلة
اكتب / لفتح قائمة إدراج بنمط Notion: /figure، /table، /section، /cite، /math.
doi:10.1145/3576915.3616679
@inproceedings{gatto24,
title = {Raft-based KV stores}, …
title = {Raft-based KV stores}, …
\cite{gatto24} inserted ✓
اقتباسات من DOI
الصق DOI أو معرّف arXiv أو عنوان URL. يجلب Oleafly بيانات BibTeX، ويزيل أي تكرار، ثم يُدرج \cite.
library.bibpapers.risendnote.xmlzotero.rdf
→ references.bib
142 entries · 9 duplicates removed ✓
أحضر مكتبتك بأكملها
استورد دفعةً واحدة من BibTeX وRIS وEndNote XML وZotero RDF. تُزال التكرارات بمقارنة كل شيء بمشروعك قبل أن يصل أي إدخال إلى ملف .bib.
⌘Krecompile
▸ Recompile document
Set recompile delay
Recompile on save
لوحة الأوامر
يبحث ⌘K بحثًا تقريبيًا في كل إجراء في التطبيق: المشاريع والملفات والإعدادات وكل شيء آخر.
ذكاء اصطناعي مستقل عن النماذج
اربط مزوّد النماذج الذي تفضّله، أو شغّل Ollama محليًا، أو استخدم وكيل CLI مثبّتًا بحسابه الخاص. اضبط وضع الموافقة بما يناسب العمل الذي بين يديك. ويعمل المحرر دون ذكاء اصطناعي أيضًا.
“raft consensus in KV stores”
alphaXiv · Ongaro & Ousterhout, 2014
DOI verified via Crossref ✓
البحث العلمي في متناول يدك
يبحث الوكيل في alphaXiv وOpenAlex، ويجلب محتوى الأوراق البحثية، ويتحقق من الاستشهادات عبر Crossref قبل إدخالها إلى قائمة مراجعك.
The experimentexpermentexperiment ran offline.
experiment · Hunspell, on-device
تدقيق لغوي مدمج
دقّق الإملاء والنحو محليًا باستخدام Hunspell وHarper. يتجاهل Oleafly أوامر LaTeX والرياضيات لتبقى الفحوص مركّزة على نصّك.
◈ task: literature review
✓ Read project sources
✓ Verify paper identifiers
Review reading-list.md
امنح البحث مساحة عمل خاصة به
اكتب موجزًا للمهمة، واختر وكيلًا، وواصل الكتابة بينما يعمل في نسخة معزولة. تابع نشاطه، وعاين الملفات المتغيّرة، وطبّق النتائج التي تريدها.
page 1page 214page 487600 pages ✓
still smooth
من صفحة واحدة إلى ستمائة
يظل المحرر وعارض PDF، الذي لا يعرض إلا الصفحات الظاهرة، سلسين سواء كان ذلك عبارة عن سيرة ذاتية من صفحة واحدة أو أطروحة بطول كتاب.
عارض PDF للقراءة الحقيقية
افصل المعاينة إلى شاشة ثانية، أو اقرأ صفحتين متقابلتين، أو اعكس الألوان في وقت متأخر من الليل، أو انتقل إلى وضع ملء الشاشة للعرض.
+−
مُنشئ المخططات
صِف مخططًا وسيكتب الذكاء الاصطناعي كود TikZ، ويجمّع الشكل بمعزل عن غيره، ويصلح التداخلات بالنظر إلى الناتج المعروض. أو ارسمه بنفسك: أشكال وحواف ولوحة خصائص على لوحة رسم حقيقية تتزامن في الاتجاهين مع كود TikZ المُنشأ. صدّر صور PNG شفافة عالية الدقة، دون اتصال بالإنترنت تمامًا.
main.texpaper.typnotes.md
one library · one Git history
ثلاثة محركات، ومساحة عمل واحدة
احتفظ بمشاريع LaTeX وTypst وMarkdown في المكتبة نفسها. اختر مجمّعًا لكل مشروع، واستخدم المعاينة والمراجع وإدارة الإصدارات وأدوات الذكاء الاصطناعي نفسها.
\begin{document}Hello, world.PDF compiled ✓
محرر LaTeX
اكتب بـ LaTeX أو Typst أو Markdown مع معاينة حيّة لملف PDF ومزامنة SyncTeX على مستوى الكلمة. المجمِّعات مضمّنة، فلا إعداد لـ TeX ولا طابور بناء.
edit→compile→verify ✓
مساعد الذكاء الاصطناعي
اطلب من المساعد تعديل مصدرك، وتجميع المشروع، وفحص ملف PDF. اربط مزوّد نماذج، أو Ollama، أو وكيل سطر أوامر مثبّتًا. وامنح الأعمال الأطول مهمة بحثية خاصة بها بينما تواصل الكتابة.
doi:10.1145/3576915@article{gatto24} ✓
مدير المراجع
استورد BibTeX أو RIS أو EndNote أو Zotero مع إزالة تلقائية للتكرار. الصق معرّف DOI أو arXiv لإنشاء مرجع موثّق عبر Crossref.
1 page ✓fork ×3 · per application
منشئ السيرة الذاتية
ابدأ بقالب سيرة ذاتية مهيّأ لأنظمة ATS، وتحقق من النص المستخرج، وتفرّع بنسخة مخصّصة لكل طلب تقديم دون فقدان النسخ السابقة.
+42 −7
إدارة الإصدارات
احتفظ بنقاط حفظ للمصدر المتغيّر بعد كل تجميع ناجح. استخدم Git لعمليات إرسال مدروسة، وقارن المراجعات، وادفع إلى GitHub من مساحة العمل نفسها.
PDFDOCXHTMLZIP
صندوق أدوات PDF
اقرأ ملفات PDF الطويلة، وأعد بناء كثير من ملفات PDF النصية إلى LaTeX، وصدّر PDF أو DOCX أو HTML أو أرشيف مصدر للتقديم.
مساحة العمل البحثية
مهمة بحثية واحدة، من البداية إلى النهاية.
كلّف وكيلًا بمهمة محددة، واقرأ التعديل المقترح، وجمّع المستند متى كنت مستعدًا. يبقى العمل مع مشروعك.
θt+1=θt−η∇θL
Typst
$ theta_(t+1) = theta_t - eta nabla_theta cal(L) $- 01أنشئ مشروعًا بحثيًاابدأ بمكان يجمع مخطوطتك ومصادرك ومهامك البحثية.
- 02كلّف وكيلًا بمهمة واحدةاختر الملفات التي يحتاجها واشرح ما تريد تغييره.
- 03راجع التغيير المقترحاقرأ الفرق بين النسختين، وقرّر أي التعديلات تنتمي إلى مخطوطتك.
- 04جمّع الملف واحتفظ بالعملتحقق من ملف PDF واستأنف لاحقًا والمهمة ما تزال في مشروعك.
Oleaflyالنوم والذاكرةسير عمل توضيحي
ابدأ عملًا جديدًا
اختر كيف تبدأ هذه المخطوطة. يبقى كل جزء منها بين يديك لتغييره.
مشروع بحثي
مجلد دراسة يضم الأقسام والمصادر وملاحظات المراجعة، ومهمة أولى تؤطّر السؤال البحثي.
استيراد مشروع
واصل مخطوطة لديك بالفعل: أرشيفًا، أو مسودة Word أو Markdown، أو مستودع GitHub.
استخدام قالب
ابدأ من تخطيط جاهز لمقال علمي أو أطروحة أو تقرير أو ملصق أو عرض تقديمي.
مشروع بحثي جديد
اختر بنية البداية وافحص كل ملف قبل أن ينشئه Oleafly.
اسم المشروع
النوم والذاكرة
محرّك المستندات
LaTeX
نقطة انطلاق الدراسة
مقال
أول مهمة بحثية
حدّد السؤال البحثي وصُغ المخطط الأولي للمقال.
معاينة المشروع
- analysis
- figures
- research
- review
- main.tex
- references.bib
\documentclass{article}
\begin{document}
\section{المنهجية}
…
\end{document}مهمة بحثية جديدة
يبقى العمل في مساحة منفصلة حتى تراجعه وتطبّقه.
البدء من
مهمة فارغة
العنوان
توضيح المنهجية
التعليمات
استخدم review/notes.md لتوضيح الاستجابات التي استبعدناها في فقرة المنهجية. اقترح تعديلًا على main.tex. اترك النتائج دون تغيير.
الوكيل والنموذج
Codexالنموذج الافتراضي
توضيح المنهجية
المراجعة مطلوبةCodexالآن
استخدم review/notes.md لتوضيح الاستجابات التي استبعدناها في فقرة المنهجية. اقترح تعديلًا على main.tex. اترك النتائج دون تغيير.
النشاطمراجعةالمخرجات
تغييرات الملفاتتغيّر ملف واحد
عاين كل ملف محدد قبل تطبيقه.
✓
main.texمعدَّل12
\section{المنهجية}13−استبعدنا الاستجابات غير المكتملة.
13+استبعدنا الاستجابات الخالية من النتيجة الأساسية.
14
برمجيمرئي
إعادة التجميعmain.tex11
…12
\section{المنهجية}13
استبعدنا الاستجابات الخالية من النتيجة الأساسية.14
15
\end{document}السجلات✓ تم تجميع ملف PDF100%
النوم والذاكرة
المنهجية
استبعدنا الاستجابات الخالية من النتيجة الأساسية.
1
ملفات المشروع والمهام البحثية تبقى معًا.
حلقة البحث
البحث والكتابة والتحقق والنشر.
انتقل من البحث في المؤلفات إلى التقديم دون أن تفقد السياق. يُبقي Oleafly مصادرك ومراجعك وأشكالك ومخرجات المجمّع وسجلك معًا في سير عمل واحد قابل للفحص.
τ=JTF
Typst
$ bold(tau) = bold(J)^T bold(F) $- doi:10.1145/3576915@article{gatto24} ✓1
بحث
ابحث في مصادر البحث المفتوحة، وحوّل معرّفات DOI وarXiv إلى BibTeX، وتحقّق من الاستشهادات قبل دخولها إلى قائمة مراجعك.
- \section{Results}2
كتابة
اكتب بـ LaTeX أو Typst أو Markdown مع القوالب وذكاء الكود على مستوى المشروع ومساعد ذكاء اصطناعي اختياري مزوّد بضوابط الموافقة.
- compiled · 0 errors ✓3
تحقق
جمّع محليًا، واقرأ أخطاء واضحة، وتنقّل بين المصدر وملف PDF. ويُظهر الاختبار المبدئي ما ستستخرجه المحللات وقارئات الشاشة.
- PDFarXivGitHub ↑4
نشر
صدّر PDF أو DOCX أو HTML، وجهّز المصدر للتقديم، وادفع إلى GitHub من المجلد نفسه الذي بدأ فيه العمل.
كيف يقارن بغيره
مساحة العمل البحثية الوحيدة المصممة لتحل محل سائر الأدوات.
اكتب وجمّع ودقّق وابحث في المؤلفات وأدر الاستشهادات وراجع ملفات PDF وأتمت التعديلات وأنجز ورقتك البحثية من مكان واحد. يجمع Oleafly منظومة البحث كاملةً في تطبيق واحد مجاني ومفتوح المصدر. اطّلع أدناه على جوانب قصور البدائل. المستندات.
| Oleafly | OpenAI Prism | Overleaf | Typst Web App | Curvenote | LyX | TeXstudio | Texifier | VS Code + LaTeX | Paperpal | Writefull | أدوات إنشاء السير الذاتية | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| الملكية والوصول | السعر | مجاني ومفتوح المصدر، بلا اشتراك في Oleafly | مجاني مع حساب ChatGPT | فئة مجانية، وتضيف الخطط المدفوعة مزايا أخرى | فئة مجانية، وPro بتكلفة إضافية | فئة مجانية، وتضيف الخطط المدفوعة مشاريع خاصة | مجاني ومفتوح المصدر | مجاني بترخيص GPL | مدفوع، مع نسخة تجريبية مجانية | مجاني، مع حدود أو خطط مدفوعة للذكاء الاصطناعي | فئة مجانية، وPrime بتكلفة إضافية | فئة مجانية، وPremium بتكلفة إضافية | يختلف، ومعظمها يعمل باشتراك |
| لا يتطلب حسابًا | نعم | لا | لا | لا | لا | نعم | نعم | نعم | نعم | لا | لا | يختلف | |
| يعمل دون اتصال | الكتابة والتدقيق والمعاينة والتجميع دون اتصال | لا، مساحة عمل سحابية | لا، خدمة سحابية | لا، يحتاج تطبيق الويب إلى اتصال | لا، فالمحرر خدمة سحابية | نعم | نعم | نعم | نعم | لا | لا | نادرًا | |
| تبقى الملفات على قرصك | مجلدات محلية عادية تملكها | تخزين سحابي | تخزين سحابي | تخزين سحابي، ويمكن تشغيل المجمّع محليًا | تخزين سحابي | نعم | نعم | ملفات محلية وموفرو ملفات | نعم | خدمة سحابية وعمليات تكامل مع المحررات | تبقى الملفات في Word أو Overleaf | تخزين سحابي عادةً | |
| سجل الإصدارات | نقاط حفظ للتجميع، إضافةً إلى إيداعات Git وعرض الفروق والاستعادة | مراجعات سحابية | السجل الكامل ضمن الخطط المدفوعة | مزامنة Git ضمن Pro | سجل إصدارات مدمج | Git وأنظمة أخرى للتحكم في الإصدارات | يدوي أو عبر SVN | يستخدم موفري الملفات أو أدوات Git | Git مدمج تضبط إعداداته بنفسك | غير موثّق | يستخدم سجل التطبيق المضيف | يختلف | |
| التعاون الفوري | قريبًا. تعاون غير محدود واستضافة ذاتية | عدد غير محدود من المتعاونين | مدمج، وتختلف الحدود باختلاف الخطة | مدمج | تحرير وتعليقات في الوقت الفعلي | لا يوجد تحرير مشترك مباشر | لا يوجد تحرير مشترك مباشر | لا يوجد تحرير مشترك مباشر | عبر Live Share | يستخدم Word أو Google Docs أو Overleaf | يستخدم Word أو Overleaf | يختلف | |
| المزامنة السحابية | قريبًا. وصول عبر المتصفح مع بقاء الملفات على جهازك | مساحة عمل سحابية | مساحة عمل سحابية مع مزامنة مدفوعة عبر Git وDropbox | مساحة عمل سحابية مع مزامنة Git ضمن Pro | مشاريع سحابية ونشر متصل | استخدم Git أو خدمة المزامنة الخاصة بك | استخدم Git أو خدمة المزامنة الخاصة بك | مزامنة مباشرة عبر Texifier Connect | استخدم Git أو خدمة المزامنة الخاصة بك | مساحة عمل سحابية | يعمل داخل Word أو Overleaf | تخزين سحابي عادةً | |
| مساحات الفرق | قريبًا. قوالب ومكتبات ومسارات مراجعة مشتركة | مشاريع مشتركة بعدد غير محدود من المتعاونين | خطط للمجموعات والمؤسسات | مشاريع مشتركة مع خيار النشر داخل المؤسسة للمنظمات | مساحات عمل للفرق وضوابط وصول | لا توجد مساحة فرق مدمجة | لا توجد مساحة فرق مدمجة | مشاريع مشتركة عبر Texifier Connect | مؤسسات GitHub وLive Share | لوحات معلومات مؤسسية وإدارة التراخيص | وصول مؤسسي | يختلف | |
| الكتابة والنشر | محركات المستندات | LaTeX وTypst وMarkdown في مساحة عمل واحدة | LaTeX فقط | LaTeX فقط | Typst فقط | MyST Markdown وJupyter | LaTeX وDocBook | LaTeX فقط | LaTeX وMarkdown | عبر الإضافات | Word وGoogle Docs والويب وOverleaf | Word وLaTeX عبر Overleaf | تنسيقات السير الذاتية فقط |
| إعداد TeX | يتضمن Tectonic وTypst، ولا يتطلب تثبيت TeX | لا يتطلب تثبيتًا، ويُجمّع في السحابة | لا يتطلب تثبيتًا، ويُجمّع في السحابة | لا يتطلب تثبيت TeX | لا يتطلب تثبيت TeX | يتطلب تثبيت توزيعة TeX | يتطلب تثبيت توزيعة TeX | منضّد ومدير حزم مدمجان | يتطلب تثبيت الإضافات وTeX | يستخدم Overleaf مع LaTeX | يستخدم Overleaf مع LaTeX | لا يتطلب إعداد TeX | |
| التحرير البرمجي والمرئي | تحرير مصدري ومرئي مع تحويل متبادل بلا فقدان | المصدر والمعاينة | المصدر ووضع النص المنسّق | المصدر ومعاينة مباشرة | محرر مرئي يدعم معادلات LaTeX | محرر مرئي منظّم | المصدر فقط | المصدر ومعاينة PDF | المصدر فقط | مساعد كتابة مرئي | اقتراحات كتابة ضمن النص | مرئي فقط | |
| فهم الشيفرة على مستوى المشروع | إكمال تلقائي مع التعريفات والمراجع وإعادة التسمية على مستوى المشروع | محرر ومساعدة بالذكاء الاصطناعي | إكمال تلقائي وبحث في المراجع | الأخطاء والإكمال وأدوات Assists | مراجع ومعادلات منظّمة | التسميات والمراجع والمخطط الهيكلي والإكمال | فاحص للبنية والمراجع | الإكمال والمخطط الهيكلي والمراجع والبحث | LaTeX Workshop IntelliSense | لا توجد أدوات لشيفرة LaTeX | TeXGPT لشيفرة LaTeX | لا | |
| مزامنة المصدر وPDF | مزامنة ثنائية الاتجاه بين المصدر وPDF على مستوى الكلمة | معاينة PDF فورية | مزامنة المصدر وPDF | معاينة مباشرة | لا توجد مزامنة بين المصدر وPDF | معاينة المصدر والمخرجات | على مستوى الكلمة تقريبًا | مزامنة المصدر وPDF | SyncTeX مباشر وعكسي | لا | يستخدم معاينة Overleaf | لا | |
| أوضاع قراءة PDF | عارض مدمج مع الفصل وعرض الصفحات المتقابلة والوضعين الداكن ووضع القراءة | معاينة مدمجة | معاينة مدمجة | معاينة مدمجة | معاينة المستند | يستخدم عارض PDF | عارض متكامل | عارض PDF متكامل | عارض عبر إضافة مع وضع عكس الألوان | محادثة مع PDF | لا يوجد قارئ PDF | معاينة المستند | |
| قوالب المستندات | أكثر من 100 قالب بداية، وقوالب مخصصة قابلة لإعادة الاستخدام، وإنشاء القوالب بالذكاء الاصطناعي | غير موثّق | معرض كبير لقوالب الناشرين | Typst Universe وقوالب Pro الخاصة | قوالب احترافية ضمن الخطط المدفوعة | فئات مستندات مدمجة | قوالب مدمجة وقوالب للمستخدم | غير موثّق | مقتطفات وقوالب من المجتمع | غير موثّق | لا | ميزة أساسية | |
| استيراد المشاريع والمستندات | ملفات وأرشيفات ZIP، إضافةً إلى PDF وDOCX وMarkdown والصور والمجلدات | مجلد أو ZIP أو سحب وإفلات | ملفات وZIP وعمليات تكامل مدفوعة | يحوّل LaTeX وWord وMarkdown | محتوى Jupyter واستيراد المراجع | LaTeX وتنسيقات نصية أخرى | فتح ملفات المصدر المحلية | مجلدات محلية وملفات سحابية | فتح ملفات المصدر المحلية | رفع ملفات PDF والمستندات | مستندات Word وOverleaf | PDF أو DOCX عادةً | |
| تنسيقات التصدير | PDF وأرشيف ZIP للمصدر، إضافةً إلى DOCX وHTML وMarkdown | PDF وملفات المشروع | PDF وأرشيف ZIP للمصدر | PDF وPNG وSVG | PDF وWord وLaTeX وTypst وMyST | PDF وHTML وWord وRTF وePub وغيرها | PDF وملفات المصدر | PDF وملفات المصدر | يعتمد على الأدوات المحلية | مسارات عمل Word | تغييرات Word المتعقبة | PDF وDOCX عادةً | |
| البحث والذكاء الاصطناعي | اختيار نموذج الذكاء الاصطناعي | مزوّدون مستضافون وOllama ونقاط نهاية مخصصة ووكلاء CLI مثبّتون | نماذج OpenAI مدمجة | ذكاء اصطناعي بحثي مدمج، ويختلف الحد اليومي باختلاف الخطة | ميزات Assists في المجمّع | غير موثّق | لا يوجد | لا يوجد | لا يوجد | Copilot أو BYOK أو إضافات | Paperpal AI | نماذج Writefull وGPT | مدمج، ويختلف اختيار النموذج |
| وكلاء CLI داخل المحرر | Claude Code وCodex وGemini CLI وغيرها | غير موثّق | غير موثّق | غير موثّق | غير موثّق | غير موثّق | غير موثّق | غير موثّق | Copilot وClaude وCodex | غير موثّق | غير موثّق | يختلف حسب المنتج | |
| استخدم اشتراكك الحالي في الذكاء الاصطناعي | استخدم اشتراك Claude أو ChatGPT عبر وكلاء CLI المدعومين | غير موثّق | غير موثّق | غير موثّق | غير موثّق | غير موثّق | غير موثّق | غير موثّق | اشتراكات الوكلاء المدعومين | غير موثّق | غير موثّق | يختلف حسب المنتج | |
| ذكاء اصطناعي محلي | Ollama محلي، من دون الحاجة إلى مزود مستضاف | لا | لا | لا | لا | لا | لا يوجد ذكاء اصطناعي مدمج | لا | BYOK أو إضافات | لا | لا | لا | |
| مراجعة تعديلات الذكاء الاصطناعي قبل تطبيقها | أوضاع الموافقة، ومعاينات التعديلات ضمن النص، ونتائج مهام قابلة للمراجعة | احتفظ أو تراجع | مراجعة اقتراحات الذكاء الاصطناعي | مراجعة كل اقتراح Assist | غير موثّق | لا يوجد ذكاء اصطناعي مدمج | لا يوجد ذكاء اصطناعي مدمج | لا يوجد ذكاء اصطناعي مدمج | مراجعة التغييرات | مراجعة اقتراحات الكتابة | تعقّب التغييرات | يختلف | |
| تحقق الذكاء الاصطناعي من النتيجة المنسّقة | يعدّل المصدر ويجمّعه ثم يفحص ملف PDF المنسّق | تعيد التجميع للتأكد | تعيد التجميع للتأكد | معاينة التجميع | لا | لا يوجد ذكاء اصطناعي مدمج | لا يوجد ذكاء اصطناعي مدمج | لا يوجد ذكاء اصطناعي مدمج | فحوص بناء من دون مراجعة PDF | لا توجد مراجعة لملف PDF المنسّق | لا توجد مراجعة لملف PDF المنسّق | لا | |
| البحث في المؤلفات والاستشهادات | بحث في المؤلفات عبر alphaXiv وOpenAlex مع التحقق بواسطة Crossref | بحث مدمج في المؤلفات | بحث في المراجع مع اقتراحات استشهاد بالذكاء الاصطناعي | لا يوجد بحث مدمج | البحث عن الاستشهادات باستخدام DOI | لا يوجد بحث مدمج | لا | لا يوجد بحث مدمج | عبر الذكاء الاصطناعي أو الإضافات | بحث في أكثر من 250 مليون مقالة | يعثر Writefull Cite على الاستشهادات الناقصة | لا | |
| مساحة البحث والمهام | المهام البحثية: مساحات عمل معزولة، ونشاط الوكيل، ومعاينات الملفات، وتطبيق انتقائي | غير موثّق | غير موثّق | لا | غير موثّق | لا | لا | لا | عبر إضافات الذكاء الاصطناعي | لا | لا | لا | |
| استيراد مكتبة المراجع | BibTeX وRIS وEndNote وZotero مع إزالة التكرارات قبل الاستيراد | مزامنة Zotero | عمليات تكامل للمراجع ضمن الخطط المدفوعة | مزامنة Zotero وMendeley ضمن Pro | Zotero وMendeley وEndNote | ملفات BibTeX | يعمل مع ملفات BibTeX | ملفات BibTeX | عبر الإضافات | مولّد استشهادات | لا يوجد استيراد للمكتبات | لا | |
| MCP لوكلاء الذكاء الاصطناعي الخارجيين | اربط أدوات MCP بالمساعد أو أتِح أدوات المشروع لوكيل خارجي | لا | لا | لا | لا | لا | لا | لا | نعم | لا | لا | لا | |
| التدقيق الإملائي والنحوي | تدقيق إملائي ونحوي خاص يعمل دون اتصال، مع فحوص نثر تراعي LaTeX | تدقيق بالذكاء الاصطناعي | تدقيق إملائي مدمج مع ملاحظات ذكاء اصطناعي مخصصة للأبحاث | غير موثّق | غير موثّق | Hunspell وAspell وقاموس مرادفات | فحوص إملائية ونحوية تفاعلية | تدقيق إملائي | عبر الإضافات أو الذكاء الاصطناعي | قواعد وأسلوب أكاديميان | ملاحظات على اللغة الأكاديمية | تختلف الفحوص الأساسية | |
| أدوات مرئية وأدوات ذكاء اصطناعي للرسوم التخطيطية | لوحة مرئية مع إنشاء TikZ بالذكاء الاصطناعي وفحص النتيجة المنسّقة | تحويل الصور والصوت إلى شيفرة | TikZ يدوي وأدوات ذكاء اصطناعي | حزم Typst وأدوات الرسم الأصلية | مخططات وأشكال تفاعلية | جداول مرئية وأدوات للصور | TikZ يدوي مع أدوات مساعدة في المحرر | TikZ يدوي | يدوي أو عبر الإضافات | لا | جداول ومعادلات وأشكال بالذكاء الاصطناعي | لا | |
| الجودة والتقديم | فحوص ما قبل التقديم | فحوص التجميع وجهة النشر وATS وإمكانية الوصول والمراجع والخصوصية | مراجعة بالذكاء الاصطناعي من دون حزمة أدوات للتقديم | فحوص التجميع | أخطاء المجمّع وأدوات Assists | أدوات الامتثال لـ SCMS | سجلات المجمّع وChkTeX اختياري | الأخطاء والتحذيرات | أخطاء واضحة من المجمّع | تحليل ساكن عبر الإضافات | أكثر من 30 فحصًا للتقديم | مراجعة جودة اللغة | فحوص السيرة الذاتية فقط |
| فحوص السيرة الذاتية لأنظمة ATS | فحوص ATS مقيّمة مع معاينة للنص المستخرج | لا | لا | لا | لا | لا | لا | لا | لا يوجد فحص مدمج | لا | لا | يختلف، وغالبًا ما تكون آلية التقييم غير واضحة | |
| فحوص إمكانية الوصول قبل التقديم | فحوص إمكانية الوصول مع التحضير للتصدير الموسوم | لا | لا | غير موثّق | نشر منظّم على الويب | مستندات منظّمة، من دون فحوص مسبقة | لا | غير موثّق | لا يوجد فحص مدمج | لا | لا | يختلف |
الخصوصية بالتحديد
المحلية بشكل افتراضي. الشبكة حسب الاختيار.
تبقى مشاريعك على جهازك. لا يستخدم Oleafly الشبكة إلا للميزات التي تختارها، ويعرض تقارير الأعطال قبل إرسالها. لا حساب في Oleafly. ولا قياس عن بُعد. خصوصية.
محلي دائمًا
- ملفات المشروع والمسودات ونقاط الحفظ وسجل Git
- الكتابة والتجميع ومراجعة PDF وفحوص ما قبل التقديم
- التدقيق الإملائي والنحوي والمخططات دون اتصال، وOllama اختياري
الشبكة، فقط عندما تطلب ذلك
- لا يتلقى الذكاء الاصطناعي المستضاف إلا السياق الذي تختار إرساله
- لا تعمل مزامنة GitHub وعمليات البحث العلمي إلا عندما تطلبها
- تُنزَّل الحزم والقوالب والخطوط وتحديثات التطبيق عند الحاجة
Edit · Compile · Commit · Verify · Research · Draft · Revise · Proofread · Cite · Search literature · Build bibliographies · Write equations · Draw diagrams · Review papers · Format manuscripts · Check references · Compare versions · Save checkpoints · Prepare submissions · Export PDFs · Import sources · Check grammar · Refine abstracts · Check accessibility ·
main.tex · refs.bib · figures/ · .git/ · LaTeX · Typst · Markdown · BibTeX · AI agents · ACP · MCP · Ollama · Tectonic · SyncTeX · DOI · arXiv · PubMed · OpenAlex · Theses · Journal articles · Conference papers · Literature reviews · Research posters · Writing tips ·
v=Km+[S]Vmax[S]
LaTeX
\[ v = \frac{V_{\max}[S]}{K_m + [S]} \]p2+2pq+q2=1
LaTeX
\[ p^2 + 2pq + q^2 = 1 \]فلسفة
يجب أن يدوم بحثك أطول من الأدوات التي استُخدمت في إنشائه.يجب أن يدوم بحثك أطول من الأدوات التي استُخدمت في إنشائه.
Yourthesisshouldn'tneedfivesubscriptions.YourAIshouldn'tguessateditsitneverchecked.Yourreferencesshouldn'ttakeanafternoon.YourfirstPDFshouldn'twaitinabuildqueue.Yourtoolsshouldn'tcostmorethanyourresearch.Onefreeapp.Allofit.
v=Km+[S]Vmax[S]
LaTeX
\[ v = \frac{V_{\max}[S]}{K_m + [S]} \]p2+2pq+q2=1
LaTeX
\[ p^2 + 2pq + q^2 = 1 \]
مفتوح المصدر، ومصمم بجدية
مستقل عن قصد. مبني من أجل المجتمع.
يُبنى Oleafly بشكل مفتوح. والموثوقية جزء من المنتج، من عمليات التجميع القابلة للإلغاء ومسارات الملفات الآمنة إلى استرداد Git والرجوع الاحتياطي إلى PDF والاختبارات على macOS وWindows وLinux.
افحص الشيفرة، أو أبلغ عن مشكلة، أو ساهم بإصلاح، أو امنح Oleafly نجمة على GitHub.
الأسئلة الشائعة
ما ينبغي معرفته قبل التحوّل.
01ما هو Oleafly؟+
Oleafly مساحة عمل مجانية لسطح المكتب مخصصة للأوراق البحثية والأطروحات والسير الذاتية وغيرها من المستندات التقنية. اكتب بـ LaTeX أو Typst أو Markdown، وعاين ملف PDF، وأدر مراجعك، واستخدم مساعد ذكاء اصطناعي اختياريًا. تبقى مشاريعك ملفات عادية على حاسوبك.
02هل هو مجاني فعلًا؟+
نعم. Oleafly مجاني ومفتوح المصدر، وتطبيق سطح المكتب لا يضيف أي اشتراك. إذا ربطت مزوّد ذكاء اصطناعي مدفوعًا، فقد يفرض ذلك المزوّد رسومًا على الاستخدام. النماذج المحلية عبر Ollama لا تتطلب واجهة برمجية مدفوعة.
03أي نماذج الذكاء الاصطناعي يعمل معها؟+
اربط مزوّد نماذج مستضافًا، أو Ollama محليًا، أو نقطة نهاية مخصصة متوافقة مع OpenAI. يمكنك أيضًا تشغيل وكلاء سطر أوامر مدعومين، بمن فيهم Claude Code وCodex، باستخدام أدواتهم وحساباتهم المثبّتة لديهم. اختر بيئة التشغيل والنموذج في المساعد.
04هل أحتاج إلى حساب؟+
لا. تطبيق سطح المكتب بلا حساب Oleafly وبلا تسجيل دخول. تبقى مشاريعك في مجلدات محلية عادية. أما خدمات الذكاء الاصطناعي وخدمات استضافة Git المربوطة فقد تتطلب بيانات اعتمادها الخاصة.
05أي الأدوات يمكنه أن يحل محلها؟+
في كثير من سير العمل، يمكن لـ Oleafly أن يحل محل أدوات منفصلة للكتابة والتدقيق والتجميع والاستشهاد وملفات PDF والسيرة الذاتية والذكاء الاصطناعي وGit. وهو يظل يعمل مع الملفات العادية وGitHub، فيمكنك اعتماده دون قفل عملك في صيغة مغلقة.
06هل يمكنني استيراد ورقة بحثية أو سيرة ذاتية موجودة؟+
نعم. افتح مجلدًا موجودًا أو استورد ملف ZIP، بما في ذلك صادرات محررات LaTeX الإلكترونية. يكتشف Oleafly المستند الرئيسي، ويمكنه تحويل ملفات PDF النصية إلى LaTeX محليًا، وتمرير DOCX عبر Pandoc، واستخدام نموذج رؤية لتفريغ نصوص الملفات الممسوحة ضوئيًا أو الصور.
07هل مخرجات PDF صديقة لأنظمة ATS؟+
تعتمد جاهزية ATS على القالب والمحتوى، لذا لا يَعِد Oleafly بدرجة معينة. تستخدم قوالب السيرة الذاتية نص Unicode قابلًا للتحديد، وخطوطًا مضمّنة، وتخطيطات أحادية العمود، وترتيب قراءة خطّيًا. ويُظهر الاختبار المبدئي ما تستخرجه أنظمة التحليل فعلًا قبل إرسال ملف PDF.
08ماذا عن التعاون والمزامنة؟+
اليوم، يتم التعاون عبر Git. انشر إلى GitHub ثم ادفع واسحب من داخل Oleafly. التحرير المشترك الفوري والتعليقات والمزامنة المُدارة مخطط لها، لكنها ليست في التطبيق بعد.
09هل يمكنني الكتابة دون اتصال أو دون ذكاء اصطناعي؟+
نعم. الكتابة والتجميع المحلي ومراجعة PDF والتدقيق اللغوي تعمل كلها دون ذكاء اصطناعي. نزّل الحزم والخطوط والأدوات التي يحتاجها مشروعك قبل الانقطاع عن الاتصال. وللذكاء الاصطناعي المحلي، نزّل نموذجًا في Ollama واربط خادمه المحلي.
10هل يمكن لوكيل أن يعمل بينما أواصل الكتابة؟+
نعم. افتح المهام البحثية، وأعطِ المهمة موجزًا، واختر وكيلًا. يعمل الوكيل في نسخة معزولة بينما تواصل العمل على الورقة البحثية. تابع النشاط، وعاين الملفات المتغيّرة، وطبّق النتائج التي تختارها.
E=hν
LaTeX
\[ E = h\nu \]تحميل
حر. مفتوح المصدر. لك.
احصل على أداة التثبيت المعدة مسبقًا من أحدث إصدار، أو بناء من المصدر. لا حساب، ولا قياس عن بُعد.
قد تُظهر بعض الإصدارات تحذيرًا من نظام التشغيل عند التشغيل لأول مرة. يشرح دليل التثبيت ما الذي يجب التحقق منه وكيفية المتابعة.