TECTONICdiagram
∇θ L(θ) = 0∑i=1n wixif(x) = α + βx + ε∫0∞ e−x² dx[ 1 0 ; 0 1 ]
NewWrite together in real time무료 · 오픈 소스 · AGPL-3.0쓰세요
쓰세요 연구 논문이력서학위논문연구비 제안서연구 논문 잡무는 줄이고.
Oleafly는 LaTeX, Typst, Markdown으로 논문을 쓰기 위한 무료 데스크톱 워크스페이스입니다. 자료를 찾고, 인용을 관리하고, 논문이 모양을 갖춰 가는 과정을 한곳에서 확인하세요. AI 어시스턴트에게 섹션 수정, 그림 제작, 깨진 빌드 수리를 맡기고 그 변경 사항을 검토할 수 있습니다. 프로젝트는 당신이 소유한 일반 파일로 남으며, 에디터는 AI와 함께 써도, AI 없이 써도 됩니다.
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
\[ a^2 + b^2 = c^2 \]
5 co-authors in results.texOleaflyTeXFix-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
Inside the app
This is what you'll be working in.
Every picture on this page is a screenshot of the app as it ships. No mockups.
New in this release
Write the paper together, in the same file.
Share a project with your co-authors and you'll see their cursors move as they type, each one labelled with a name. Comments sit next to the line they're about. If your train loses Wi-Fi, keep writing. Your edits go through when you reconnect.
How to set up a server
Named cursors
You can tell at a glance who is in the methods section and who is fixing Table 1.
Comments on the line
Ask a question on a sentence and mark it resolved when it's fixed.
See who's here
Avatars show who's in the project and which file they're working in.
Run your own server
Install Oleafly Server on a machine your group controls with one command.
Write and compile
Source on one side, the PDF on the other.
Tectonic and Typst are bundled, so most projects compile the first time you open them. Click a spot in the PDF and the editor jumps to the line behind it. If a build breaks, the last good PDF stays on screen while you fix it.
- Completion for commands, labels and citation keys
- Spelling and grammar checks that never leave your computer
- Switch between Code and Visual view
AI assistant
Ask for help. Read the diff. Then decide.
The assistant can read your project, run a compile, fix the error it finds or draft a TikZ figure. Each edit shows up as a diff you can review and undo. Bring a hosted model or your own endpoint, or run Ollama and keep it all on your machine.
- Plan mode reads the project before it writes anything
- Turn AI off and the rest of the app works the same
Citations
Find the paper and cite it without opening a browser.
Citation Search looks through arXiv, Semantic Scholar, Crossref, PubMed and OpenAlex at once. Save a result and its BibTeX goes into your .bib file. Got a DOI or an arXiv ID? Paste it and Oleafly fills in the rest.
- Imports Zotero, EndNote, RIS and BibTeX
- Flags undefined and duplicate keys as you type
Version history
Git in the sidebar, and checkpoints when you don't want Git.
Stage, diff, commit, push and pull without leaving the editor. Separately, Oleafly saves a local checkpoint after each successful compile, so going back an hour doesn't need a commit.
- Unified or side-by-side diffs
- Publish a project to GitHub from the app
LaTeX, Typst and Markdown
Write in the format your venue asks for.
LaTeX compiles with the bundled Tectonic or your own TeX install. Typst has its own bundled compiler, and Markdown goes through Pandoc. The outline, the structure map and the live preview work the same way in all three.
- Compilers come with the app, so there's no TeX install to fight
- Convert between LaTeX, Typst and Word from the Tools gallery
And the rest
The parts you notice on deadline day.
Preflight
Before you submit, check the layout, accessibility, references and anything that would break blind review.
Draw it, get TikZ
Put boxes and arrows on a canvas, then switch to the TikZ source and keep editing.
Cite as you type
Type \cite{ and pick from your .bib file and Zotero library, with authors and year beside each key.
A version for every compile
Each successful compile that changed the source is kept. Go back to any of them in one click.
Template packs
Download a pack of conference, journal or thesis templates. Once it's on your machine, every template compiles offline.
Bring your work in
Start from a .zip, a Word or Markdown file, an arXiv paper or a GitHub repo. The original stays untouched.
Bring your own agent
Connect Claude Code, Codex CLI, Gemini CLI and other command-line agents through ACP.
47 free tools
PDF to LaTeX, arXiv to Typst, spreadsheets to tables, BibTeX checks and more. No project needed.
Keyboard first
Jump to a file, run a command or open a tool without touching the mouse.
Projects are folders
Every project is a normal folder on disk. Open it in anything.
An admin console for your server
Add people, set roles and see their devices on the collaboration server your group runs.
Back up to Dropbox
Keep your Library in your own Dropbox and open it on your other computers. Keys and AI chats stay on this one.
강력한 연구 하네스
첫 인용부터 최종 PDF까지.
별도 도구를 엮지 않고도 초안 작성, 컴파일, 교정, 검색, 인용, 검토, 출판까지. Oleafly는 소스, 미리보기, 참고문헌, AI, Git 기록을 당신이 통제하는 하나의 워크스페이스에 둡니다.
paper.pdfmain.texlocal ✓
가진 것을 가져오기
텍스트 PDF를 편집 가능한 LaTeX로 로컬 재구성, 관리 Pandoc으로 DOCX 변환, 페이지 사진을 비전 모델로 전사. 이후 AI 다듬기는 선택.
main.tex→PDFDOCXHTML
갈 곳으로 내보내기
컨텍스트 메뉴에서 PDF, DOCX, HTML, Markdown 등으로 내보낼 수 있습니다. 프로젝트 전체를 소스 ZIP으로 내려받을 수도 있습니다.
-- NORMAL --:wq
accent · themes · layouts
내 손맛에 맞게
Vim 모드, 라이트·다크, 액센트 색, 레이아웃 7종, 편집 가능한 단축키. 에디터는 손에 맞아야 합니다.
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
코드 또는 비주얼로 쓰기
LaTeX·Markdown을 비주얼 편집으로: 제목, 목록, 굵게, 링크를 직접. 두 모드 연동 실행 취소. 미지원 명령은 조용히 지우지 않고 raw 블록으로 남겨 소스 왕복이 비파괴.
main.tex
\section{Results}
We evaluate on
\cite{gatto24}
PDF
단어 단위 SyncTeX
PDF 단어를 ⌘-클릭하면 소스의 그 단어로. ⌘⇧J로 돌아감.
F2 · rename symbol
intro.tex \ref{fig:pipelinefig:pipelinefig:arch}
results.tex \ref{fig:pipelinefig:pipelinefig:arch}
코드 인텔리전스
정의로 이동, 참조 찾기, 레이블·인용 키·매크로를 모든 파일에서 이름 바꾸기.
…shown in Figure 3. /fig
/figure
/table
/cite
슬래시 명령
/ 로 Notion 스타일 메뉴: /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 ✓
DOI로 인용
DOI, arXiv id, URL 붙여넣기. BibTeX를 가져와 중복 제거하고 \cite 삽입.
library.bibpapers.risendnote.xmlzotero.rdf
→ references.bib
142 entries · 9 duplicates removed ✓
라이브러리 통째로
BibTeX, RIS, EndNote XML, Zotero RDF 일괄 가져오기. .bib에 들어가기 전 프로젝트와 중복 제거.
⌘Krecompile
▸ Recompile document
Set recompile delay
Recompile on save
명령 팔레트
⌘K로 앱의 모든 동작을 퍼지 검색: 프로젝트, 파일, 설정 등.
모델에 구애받지 않는 AI
원하는 모델 제공자를 연결하거나, Ollama를 로컬에서 실행하거나, 설치된 CLI 에이전트를 자체 계정으로 사용하세요. 작업에 맞게 승인 모드를 설정할 수 있습니다. 에디터는 AI 없이도 동작합니다.
“raft consensus in KV stores”
alphaXiv · Ongaro & Ousterhout, 2014
DOI verified via Crossref ✓
조사는 바로
에이전트가 alphaXiv·OpenAlex를 검색하고 본문을 가져오며, 참고문헌에 넣기 전 Crossref로 인용 검증.
The experimentexpermentexperiment ran offline.
experiment · Hunspell, on-device
내장 교정 기능
Hunspell과 Harper로 맞춤법과 문법을 로컬에서 교정합니다. Oleafly는 LaTeX 명령과 수식을 무시하므로 검사가 본문에 집중됩니다.
◈ task: literature review
✓ Read project sources
✓ Verify paper identifiers
Review reading-list.md
연구에 전용 워크스페이스를
작업 개요를 쓰고 에이전트를 고르면, 에이전트가 격리된 사본에서 작업하는 동안 계속 초안을 쓸 수 있습니다. 활동을 따라가고, 변경된 파일을 미리 보고, 원하는 결과를 적용하세요.
page 1page 214page 487600 pages ✓
still smooth
한 장에서 육백 장까지
한 장 이력서든 책 분량 학위논문이든 에디터와 가상화 PDF가 부드럽게.
진짜 읽기를 위한 PDF 뷰어
미리보기를 두 번째 모니터로, 두 페이지 펼침, 야간 색 반전, 전체 화면 발표.
+−
다이어그램 작성기
도식을 설명하면 AI가 TikZ를 쓰고 단독 컴파일하며 렌더를 보고 겹침을 고침. 직접 도형·선을 그려도 생성 TikZ와 왕복. 투명 고해상 PNG 오프라인 내보내기.
main.texpaper.typnotes.md
one library · one Git history
엔진 셋, 워크스페이스 하나
LaTeX, Typst, Markdown 프로젝트를 같은 라이브러리에 두세요. 프로젝트마다 컴파일러를 고르고, 같은 미리보기, 참고문헌, 버전 관리, AI 도구를 사용합니다.
\begin{document}Hello, world.PDF compiled ✓
LaTeX 에디터
LaTeX, Typst, Markdown으로 쓰면서 실시간 PDF 미리보기와 단어 단위 SyncTeX까지. 컴파일러가 포함되어 있어 TeX 설정도 빌드 대기열도 없습니다.
edit→compile→verify ✓
AI 어시스턴트
어시스턴트에게 소스 편집, 프로젝트 컴파일, PDF 검사를 맡기세요. 모델 제공자, Ollama, 설치된 CLI 에이전트를 연결할 수 있습니다. 긴 작업은 별도의 연구 작업으로 돌리고 계속 쓰세요.
doi:10.1145/3576915@article{gatto24} ✓
참고문헌 관리자
BibTeX, RIS, EndNote, Zotero를 자동 중복 제거와 함께 가져오세요. DOI나 arXiv ID를 붙여넣으면 Crossref로 검증된 참고문헌이 만들어집니다.
1 page ✓fork ×3 · per application
이력서 빌더
ATS 중심 이력서 템플릿으로 시작하고, 추출된 텍스트를 확인하고, 지원 건마다 맞춤 사본을 포크하되 이전 버전은 잃지 않습니다.
+42 −7
버전 관리
컴파일 성공 후 변경된 소스를 체크포인트로 남깁니다. Git으로 의도적인 커밋을 하고, 리비전을 비교하고, 같은 워크스페이스에서 GitHub로 푸시하세요.
PDFDOCXHTMLZIP
PDF 툴킷
긴 PDF를 읽고, 텍스트 기반 PDF 다수를 LaTeX로 재구성하고, 제출용으로 PDF, DOCX, HTML 또는 소스 아카이브로 내보내세요.
연구 워크스페이스
연구 작업 하나, 처음부터 끝까지.
에이전트에게 집중된 작업 하나를 맡기고, 제안된 수정을 읽고, 준비되면 컴파일하세요. 작업 결과는 프로젝트와 함께 남습니다.
θt+1=θt−η∇θL
Typst
$ theta_(t+1) = theta_t - eta nabla_theta cal(L) $- 01연구 프로젝트 만들기원고, 출처, 연구 작업을 둘 공간부터 시작하세요.
- 02에이전트에게 작업 하나 맡기기에이전트에 필요한 파일을 고르고 바꾸고 싶은 것을 설명하세요.
- 03제안된 변경 검토하기diff를 읽고, 어떤 편집이 원고에 들어갈지 정하세요.
- 04컴파일하고 결과 남기기PDF를 확인하세요. 작업은 프로젝트에 남아 나중에 이어서 할 수 있습니다.
Oleafly수면과 기억예시 워크플로
새 작업 시작하기
원고를 어떻게 시작할지 고르세요. 모든 부분은 당신의 것이며 언제든 바꿀 수 있습니다.
연구 프로젝트
섹션과 출처, 검토 노트, 연구 질문을 세워 주는 첫 작업이 담긴 연구용 폴더.
프로젝트 가져오기
이미 있던 원고를 이어서 작업하세요: 아카이브, Word 또는 Markdown 초고, GitHub 저장소.
템플릿 사용
저널 논문, 학위논문, 보고서, 포스터, 발표용으로 준비된 레이아웃으로 시작하세요.
새 연구 프로젝트
시작 구조를 고르고, Oleafly가 만들기 전에 모든 파일을 하나하나 확인하세요.
프로젝트 이름
수면과 기억
문서 엔진
LaTeX
연구 스타터
논문
첫 연구 작업
연구 질문을 정의하고 논문 개요 초안을 작성합니다.
프로젝트 미리보기
- analysis
- figures
- research
- review
- main.tex
- references.bib
\documentclass{article}
\begin{document}
\section{방법}
…
\end{document}새 연구 작업
작업 결과는 검토하고 적용할 때까지 별도의 워크스페이스에 머뭅니다.
시작 방식
빈 작업
제목
방법 명확히 하기
지시 사항
review/notes.md를 활용해 방법 문단에서 어떤 응답을 제외했는지 명확히 하세요. main.tex에 대한 수정을 제안하고, 결과는 그대로 두세요.
에이전트 및 모델
Codex기본 모델
코드비주얼
재컴파일main.tex11
…12
\section{방법}13
일차 결과가 누락된 응답은 제외했다.14
15
\end{document}로그✓ PDF 컴파일됨100%
수면과 기억
방법
일차 결과가 누락된 응답은 제외했다.
1
프로젝트 파일과 연구 작업이 한곳에 함께 남습니다.
연구 루프
조사하고, 쓰고, 검증하고, 발표합니다.
문헌 검색부터 제출까지 맥락을 잃지 않고 이어 가세요. Oleafly는 소스, 참고문헌, 그림, 컴파일러 출력, 기록을 검사 가능한 하나의 워크플로에 함께 둡니다.
τ=JTF
Typst
$ bold(tau) = bold(J)^T bold(F) $- doi:10.1145/3576915@article{gatto24} ✓1
조사
공개 연구 자료를 검색하고, DOI와 arXiv ID를 BibTeX로 바꾸고, 참고문헌에 들어가기 전에 인용을 검증합니다.
- \section{Results}2
작성
템플릿, 프로젝트 전체 코드 인텔리전스, 승인 제어가 있는 선택적 AI 어시스턴트와 함께 LaTeX, Typst, Markdown으로 작성합니다.
- compiled · 0 errors ✓3
검증
로컬에서 컴파일하고, 명확한 오류를 읽고, 소스와 PDF 사이를 오갑니다. 사전 점검은 파서와 스크린 리더가 추출할 내용을 보여 줍니다.
- PDFarXivGitHub ↑4
발표
PDF, DOCX, HTML로 내보내고, 제출용으로 소스를 패키징하고, 작업을 시작한 바로 그 폴더에서 GitHub로 푸시합니다.
제품 비교
다른 모든 도구를 대체하도록 설계된 하나의 연구 작업 공간.
한곳에서 작성하고, 컴파일하고, 교정하고, 문헌을 검색하고, 인용을 관리하고, PDF를 검토하고, 편집을 자동화해 논문 제출까지 마치세요. Oleafly는 전체 연구 도구를 하나의 무료 오픈 소스 앱에 담았습니다. 아래에서 다른 대안에 부족한 점을 확인해 보세요. 문서.
| Oleafly | OpenAI Prism | Overleaf | Typst Web App | Curvenote | LyX | TeXstudio | Texifier | VS Code + LaTeX | Paperpal | Writefull | 이력서 빌더 | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 소유권 및 접근 | 가격 | 무료 오픈 소스. Oleafly 구독 불필요 | ChatGPT 계정으로 무료 이용 | 무료 요금제. 유료 요금제에서 기능 추가 | 무료 요금제. Pro는 추가 비용 | 무료 요금제. 유료 요금제에서 비공개 프로젝트 추가 | 무료 오픈 소스 | 무료, GPL | 유료. 무료 데모 제공 | 무료. AI에는 사용량 제한 또는 유료 요금제 적용 | 무료 요금제. Prime은 추가 비용 | 무료 요금제. Premium은 추가 비용 | 서비스별로 다름. 대부분 구독제 |
| 계정 불필요 | 예 | 아니요 | 아니요 | 아니요 | 아니요 | 예 | 예 | 예 | 예 | 아니요 | 아니요 | 서비스별로 다름 | |
| Platforms | macOS, Windows and Linux desktop apps | Web only | Web, plus self-hosted Server Pro | Web, plus an on-premises plan | Web editor plus open-source CLI | Windows, macOS and Linux | Windows, macOS and Linux | macOS and iOS. Windows coming | Windows, macOS and Linux | Web, Word, Google Docs, Overleaf | Word, Overleaf and web | Mostly web | |
| 오프라인 작동 | 오프라인에서 작성, 교정, 미리보기 및 컴파일 가능 | 아니요. 클라우드 작업 공간 | 아니요. 클라우드 서비스 | 아니요. 웹 앱은 인터넷 연결 필요 | 아니요. 편집기는 클라우드 서비스 | 예 | 예 | 예 | 예 | 아니요 | 아니요 | 거의 지원하지 않음 | |
| Interface languages | 21 interface languages | Not documented | 18 | Not documented | Not documented | 26, varying completeness | About 30 community translations | 8 | 15 | Not documented | Not documented | Varies by product | |
| 파일을 내 디스크에 보관 | 직접 소유하는 일반 로컬 폴더 | 클라우드 저장소 | 클라우드 저장소 | 클라우드 저장소. 컴파일러는 로컬에서 실행 가능 | 클라우드 저장소 | 예 | 예 | 로컬 파일 및 파일 제공업체 | 예 | 클라우드 서비스 및 편집기 연동 | 파일을 Word 또는 Overleaf에 유지 | 대부분 클라우드 저장소 | |
| Collaboration and sync | 실시간 공동 작업 | 출시 예정. 무제한 공동 작업. 자체 호스팅 | 공동 작업자 무제한 | 기본 제공. 요금제에 따라 제한 | 기본 제공 | 실시간 편집 및 댓글 | 실시간 공동 편집 없음 | 실시간 공동 편집 없음 | 실시간 공동 편집 없음 | Live Share 이용 | Word, Google Docs 또는 Overleaf 이용 | Word 또는 Overleaf 이용 | 서비스별로 다름 |
| Live comments | Threads with replies, @mentions and resolve | Yes | Yes | Yes, owner needs Pro | Yes | No | No | Not documented | Via extensions only | In the host editor only | In the host editor only | Rarely | |
| Your own server | Oleafly Server: one-command install, admin console, SSO | No | Yes | On-premises plan | Not documented | No | Peer-to-peer, one user hosts | Not documented | No. Live Share is Microsoft-hosted | Not documented | Not documented | Rarely | |
| 클라우드 동기화 | 출시 예정. 파일은 내 컴퓨터에 유지하면서 브라우저로 접근 | 클라우드 작업 공간 | 클라우드 작업 공간과 유료 Git 및 Dropbox 동기화 | 클라우드 작업 공간과 Pro Git 동기화 | 클라우드 프로젝트 및 연계 출판 | Git 또는 자체 동기화 서비스 이용 | Git 또는 자체 동기화 서비스 이용 | Texifier Connect 실시간 동기화 | Git 또는 자체 동기화 서비스 이용 | 클라우드 작업 공간 | Word 또는 Overleaf 내에서 작동 | 대부분 클라우드 저장소 | |
| 팀 공간 | 출시 예정. 공유 템플릿, 라이브러리 및 검토 워크플로 | 공동 작업자 수 제한 없는 공유 프로젝트 | 그룹 및 기관 요금제 | 공유 프로젝트 및 조직용 온프레미스 배포 | 팀 작업 공간 및 접근 제어 | 내장 팀 공간 없음 | 내장 팀 공간 없음 | Texifier Connect를 통한 공유 프로젝트 | GitHub 조직 및 Live Share | 기관용 대시보드 및 라이선스 관리 | 기관용 접근 | 서비스별로 다름 | |
| 버전 기록 | 저장된 컴파일 체크포인트와 Git 커밋, diff, 복원 | 클라우드 수정 기록 | 유료 요금제에서 전체 기록 제공 | Pro에서 Git 동기화 | 버전 기록 내장 | Git 및 기타 버전 관리 | 수동 또는 SVN | 파일 제공업체 또는 Git 도구 이용 | 직접 설정하는 내장 Git | 공식 문서에 명시되지 않음 | 호스트 앱의 기록 이용 | 서비스별로 다름 | |
| Git and GitHub | Built-in Git panel. Publish, push and pull to GitHub | Not yet. Planned | Git and GitHub on paid plans | GitHub and GitLab sync on Pro, experimental | GitHub integration and CLI | Basic, local only | Built-in Git panel and SVN | Not documented | Built in | Not documented | Not documented | No | |
| 작성 및 출판 | 문서 엔진 | 하나의 작업 공간에서 LaTeX, Typst 및 Markdown 지원 | LaTeX만 지원 | LaTeX만 지원 | Typst만 지원 | MyST Markdown 및 Jupyter | LaTeX 및 DocBook | LaTeX만 지원 | LaTeX 및 Markdown | 확장 프로그램으로 지원 | Word, Google Docs, 웹 및 Overleaf | Word 및 Overleaf LaTeX | 이력서 형식만 지원 |
| TeX 설정 | Tectonic 및 Typst 포함. TeX 설치 불필요 | 설치 불필요. 클라우드에서 컴파일 | 설치 불필요. 클라우드에서 컴파일 | TeX 설치 불필요 | TeX 설치 불필요 | TeX 배포판 설치 필요 | TeX 배포판 설치 필요 | 조판 엔진 및 패키지 관리자 내장 | 확장 프로그램 및 TeX 설치 필요 | LaTeX 작업에 Overleaf 이용 | LaTeX 작업에 Overleaf 이용 | TeX 설정 불필요 | |
| 코드 및 시각적 편집 | 손실 없는 양방향 변환을 지원하는 소스 및 시각적 편집 | 소스 및 미리보기 | 소스 및 리치 텍스트 모드 | 소스 및 실시간 미리보기 | LaTeX 수식을 지원하는 시각적 편집기 | 구조화된 시각적 편집기 | 소스 편집만 지원 | 소스 및 PDF 미리보기 | 소스 편집만 지원 | 시각적 글쓰기 도우미 | 인라인 글쓰기 제안 | 시각적 편집만 지원 | |
| 프로젝트 전체 코드 인텔리전스 | 자동 완성과 정의, 참조 및 프로젝트 전체 이름 변경 | 편집기 및 AI 지원 | 자동 완성 및 참조 검색 | 오류, 자동 완성 및 Assists | 구조화된 참조 및 수식 | 레이블, 참조, 개요 및 자동 완성 | 구조 및 참조 검사기 | 자동 완성, 개요, 참조 및 검색 | LaTeX Workshop IntelliSense | LaTeX 코드 도구 없음 | LaTeX 코드용 TeXGPT | 아니요 | |
| 소스 및 PDF 동기화 | 단어 단위의 양방향 소스 및 PDF 동기화 | 즉시 PDF 미리보기 | 소스 및 PDF 동기화 | 실시간 미리보기 | 소스 및 PDF 동기화 없음 | 소스 및 출력 미리보기 | 거의 단어 단위로 지원 | 소스 및 PDF 동기화 | 정방향 및 역방향 SyncTeX | 아니요 | Overleaf 미리보기 이용 | 아니요 | |
| PDF 읽기 모드 | 내장 뷰어와 분리 창, 펼침면, 다크 및 리더 모드 | 내장 미리보기 | 내장 미리보기 | 내장 미리보기 | 문서 미리보기 | PDF 뷰어 사용 | 통합 뷰어 | 통합 PDF 뷰어 | 색상 반전 모드를 갖춘 확장 프로그램 뷰어 | PDF와 대화 | PDF 리더 없음 | 문서 미리보기 | |
| 문서 템플릿 | 100개 이상의 시작 템플릿, 재사용 가능한 사용자 템플릿, AI 템플릿 생성 | 공식 문서에 명시되지 않음 | 대규모 출판사 템플릿 갤러리 | Typst Universe 및 Pro 전용 비공개 템플릿 | 유료 요금제에서 전문 템플릿 제공 | 내장 문서 클래스 | 내장 및 사용자 템플릿 | 공식 문서에 명시되지 않음 | 스니펫 및 커뮤니티 템플릿 | 공식 문서에 명시되지 않음 | 아니요 | 핵심 기능 | |
| 프로젝트 및 문서 가져오기 | 파일과 ZIP은 물론 PDF, DOCX, Markdown, 이미지 및 폴더 지원 | 폴더, ZIP 또는 드래그 앤 드롭 | 파일, ZIP 및 유료 연동 기능 | LaTeX, Word 및 Markdown 변환 | Jupyter 콘텐츠 및 참고문헌 가져오기 | LaTeX 및 기타 텍스트 형식 | 로컬 소스 파일 열기 | 로컬 폴더 및 클라우드 파일 | 로컬 소스 파일 열기 | PDF 및 문서 업로드 | Word 및 Overleaf 문서 | 대부분 PDF 또는 DOCX | |
| 내보내기 형식 | PDF 및 소스 ZIP과 DOCX, HTML, Markdown | PDF 및 프로젝트 파일 | PDF 및 소스 ZIP | PDF, PNG 및 SVG | PDF, Word, LaTeX, Typst 및 MyST | PDF, HTML, Word, RTF, ePub 등 | PDF 및 소스 파일 | PDF 및 소스 파일 | 로컬 도구에 따라 다름 | Word 워크플로 | Word 변경 내용 추적 | 대부분 PDF 및 DOCX | |
| 시각적 다이어그램 및 AI 도구 | 시각적 캔버스와 렌더링 검사를 포함한 AI 생성 TikZ | 이미지와 음성을 코드로 변환 | 수동 TikZ 및 AI 도구 | Typst 패키지 및 네이티브 그리기 기능 | 대화형 차트 및 도표 | 시각적 표 및 이미지 도구 | 편집기 지원을 활용한 수동 TikZ | 수동 TikZ | 수동 작성 또는 확장 프로그램 | 아니요 | AI 표, 수식 및 도표 | 아니요 | |
| Built-in tools | 47 converters plus citation and math tools | Image and voice to LaTeX | No dedicated gallery | Not documented | Not documented | No | Table, figure and quick-start wizards | Not documented | Via extensions | Paraphraser, translator, citations, PDF chat | Paraphraser, academizer, title and abstract generators | ATS checkers and cover letter generators | |
| 연구 및 AI | AI 모델 선택 | +4호스팅 제공업체, Ollama, 사용자 지정 엔드포인트, 설치된 CLI 에이전트 | OpenAI 모델 내장 | 연구용 AI 내장. 일일 사용량은 요금제에 따라 다름 | 컴파일러 Assists | 공식 문서에 명시되지 않음 | 없음 | 없음 | 없음 | Copilot, BYOK 또는 확장 프로그램 | Paperpal AI | Writefull 모델 및 GPT | 내장. 모델 선택지는 서비스별로 다름 |
| 편집기 안의 CLI 에이전트 | +7Claude Code, Codex, Gemini CLI 등 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | Copilot, Claude, Codex | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 제품에 따라 다름 | |
| 로컬 AI | 로컬 Ollama. 호스팅 제공업체 불필요 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 내장 AI 없음 | 아니요 | BYOK 또는 확장 프로그램 | 아니요 | 아니요 | 아니요 | |
| AI 편집 내용 검토 후 적용 | 승인 모드, 인라인 편집 미리보기, 검토 가능한 작업 결과 | 유지 또는 실행 취소 | AI 제안 검토 | 각 Assist 개별 검토 | 공식 문서에 명시되지 않음 | 내장 AI 없음 | 내장 AI 없음 | 내장 AI 없음 | 변경 사항 검토 | 글쓰기 제안 검토 | 변경 내용 추적 | 서비스별로 다름 | |
| AI의 렌더링 결과 확인 | 소스를 편집하고 컴파일한 다음 렌더링된 PDF 확인 | 사용자가 다시 컴파일해 확인 | 사용자가 다시 컴파일해 확인 | 컴파일 미리보기 | 아니요 | 내장 AI 없음 | 내장 AI 없음 | 내장 AI 없음 | PDF 검토 없는 빌드 검사 | 렌더링된 PDF 검토 없음 | 렌더링된 PDF 검토 없음 | 아니요 | |
| AI skills | 36 research skills built in, more to download | Built-in skills such as Paper Review | One built-in claim scan | No AI assistant | Not documented | No AI assistant | Editable prompt and AI macros | No AI assistant | Yes | Preset and custom prompts | Not documented | Custom prompts at most | |
| 문헌 및 인용 검색 | alphaXiv 및 OpenAlex의 문헌 검색과 Crossref 검증 | 문헌 검색 내장 | 참고문헌 검색 및 AI 인용 제안 | 내장 검색 없음 | DOI 인용 조회 | 내장 검색 없음 | 아니요 | 내장 검색 없음 | AI 또는 확장 프로그램으로 지원 | 2억 5천만 편 이상의 논문 검색 | Writefull Cite로 누락된 인용 검색 | 아니요 | |
| 연구 작업 공간과 작업 | 연구 작업: 격리된 작업 공간, 에이전트 활동, 파일 미리보기, 선택적 적용 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | 아니요 | 공식 문서에 명시되지 않음 | 아니요 | 아니요 | 아니요 | AI 확장 프로그램으로 지원 | 아니요 | 아니요 | 아니요 | |
| 참고문헌 라이브러리 가져오기 | BibTeX, RIS, EndNote 및 Zotero 지원과 가져오기 전 중복 제거 | Zotero 동기화 | 유료 요금제에서 참고문헌 연동 제공 | Pro에서 Zotero 및 Mendeley 동기화 | Zotero, Mendeley 및 EndNote | BibTeX 파일 | BibTeX 파일 지원 | BibTeX 파일 | 확장 프로그램으로 지원 | 인용 생성기 | 라이브러리 가져오기 없음 | 아니요 | |
| 외부 AI 에이전트용 MCP | MCP 도구를 어시스턴트에 연결하거나 프로젝트 도구를 외부 에이전트에 제공 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 예 | 아니요 | 아니요 | 아니요 | |
| 품질 및 제출 | 제출 전 점검 | 컴파일 검사와 제출처, ATS, 접근성, 참고문헌 및 개인정보 점검 | 제출 도구 모음 없이 AI 검토만 제공 | 컴파일 검사 | 컴파일러 오류 및 Assists | SCMS 규정 준수 도구 | 컴파일러 로그 및 선택적 ChkTeX | 오류 및 경고 | 명확한 컴파일러 오류 | 확장 프로그램을 통한 린팅 | 30개 이상의 제출 검사 | 언어 품질 검토 | 이력서 검사만 지원 |
| 맞춤법 및 문법 검사 | LaTeX 인식 산문 검사를 갖춘 비공개 오프라인 맞춤법 및 문법 검사 | AI 교정 | 맞춤법 검사 내장 및 연구 문서에 특화된 AI 피드백 | 공식 문서에 명시되지 않음 | 공식 문서에 명시되지 않음 | Hunspell, Aspell 및 동의어 사전 | 대화형 맞춤법 및 문법 검사 | 맞춤법 검사 | 확장 프로그램 또는 AI로 지원 | 학술 문법 및 문체 | 학술 언어 피드백 | 기본 검사 기능은 서비스별로 다름 | |
| 이력서 ATS 검사 | 점수 기반 ATS 검사 및 추출된 텍스트 미리보기 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 아니요 | 내장 검사 없음 | 아니요 | 아니요 | 서비스별로 다름. 채점 기준은 불명확한 경우가 많음 | |
| 접근성 사전 점검 | 접근성 검사 및 태그 지정 내보내기 준비 | 아니요 | 아니요 | 공식 문서에 명시되지 않음 | 구조화된 웹 출판 | 구조화된 문서. 사전 점검 없음 | 아니요 | 공식 문서에 명시되지 않음 | 내장 검사 없음 | 아니요 | 아니요 | 서비스별로 다름 | |
| Blind-review checks | Flags author names, acknowledgements, PDF metadata and comments | Not documented | Not documented | Not documented | No | Not documented | Not documented | Not documented | Not documented | Not documented | Not documented | No | |
| Reference and file checks | Undefined refs, missing files, duplicate keys, uncited entries | AI error fixes and Paper Review | AI .bib and claim checks | Compiler errors on missing labels | DOI, link, cross-reference and image checks | Marks broken cross-references | Live reference checking | LaTeX error list only | ChkTeX and LaCheck linting | 30+ checks including references and figures | Flags uncited claims (institutions) | No | |
| Word count and insights | Word count plus headings, figures, tables, citations and TODOs | Not documented | Yes | Not documented | Abstract word-limit check | Yes | Yes | Yes | Yes, via TeXcount | Not documented | Not documented | Resume analysis scores |
프라이버시를 정확히
기본은 로컬. 네트워크는 선택일 때.
프로젝트는 당신의 기기에 남습니다. Oleafly는 당신이 선택한 기능에만 네트워크를 사용하며, 충돌 보고서는 보내기 전에 보여 줍니다. Oleafly 계정 없음. 원격 측정 없음. 개인정보 보호.
항상 로컬
Works with the Wi-Fi off
- 프로젝트 파일, 초안, 저장된 체크포인트, Git 기록
- 작성, 컴파일, PDF 검토, 사전 점검
- 오프라인 맞춤법 검사, 문법 검사, 다이어그램, 선택적 Ollama
행동할 때만 네트워크
Only when you click
- 호스팅 AI는 당신이 보내기로 선택한 컨텍스트만 받음
- GitHub 동기화와 연구 검색은 요청할 때 실행
- 패키지, 템플릿, 글꼴, 앱 업데이트는 필요할 때 다운로드
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
\[ p^2 + 2pq + q^2 = 1 \]철학
연구는 그것을 만든 도구보다 오래 남아야 합니다.연구는 그것을 만든 도구보다 오래 남아야 합니다.
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
\[ p^2 + 2pq + q^2 = 1 \]
진지한 오픈 소스
설계부터 독립적. 커뮤니티를 위해 만듭니다.
Oleafly는 공개적으로 개발됩니다. 취소 가능한 컴파일과 안전한 파일 경로부터 Git 복구, PDF 폴백, macOS·Windows·Linux 전반의 테스트까지, 신뢰성도 제품의 일부입니다.
코드를 살펴보고, 이슈를 보고하고, 수정을 기여하거나 Oleafly에 Star를 주려면: GitHub.
자주 묻는 질문
옮기기 전에 알아둘 것들.
Didn't find your answer? Ask on Discord or GitHub Discussions.
01Oleafly란 무엇인가요?+
Oleafly는 논문, 학위논문, 이력서 등 기술 문서를 위한 무료 데스크톱 워크스페이스입니다. LaTeX, Typst, Markdown으로 쓰고, PDF를 미리보고, 참고문헌을 관리하고, 선택적으로 AI 어시스턴트를 쓸 수 있습니다. 프로젝트는 컴퓨터의 일반 파일로 남습니다.
02정말 무료인가요?+
네. Oleafly는 무료 오픈 소스입니다. 데스크톱 앱은 구독을 추가하지 않습니다. 유료 AI 제공자를 연결하면 해당 제공자가 사용량을 청구할 수 있습니다. Ollama의 로컬 모델은 유료 API가 필요 없습니다.
03어떤 AI 모델과 함께 쓸 수 있나요?+
호스팅 모델 제공자, 로컬 Ollama, 또는 OpenAI 호환 커스텀 엔드포인트를 연결하세요. Claude Code와 Codex를 포함한 지원 CLI 에이전트를 각자 설치된 도구와 계정으로 실행할 수도 있습니다. 런타임과 모델은 어시스턴트에서 고르세요.
04계정이 필요한가요?+
아니요. 데스크톱 앱에는 Oleafly 계정이나 로그인이 없습니다. 프로젝트는 일반 로컬 폴더에 남습니다. 연결한 AI 및 Git 호스팅 서비스에는 각자의 자격 증명이 필요할 수 있습니다.
05어떤 도구를 대체할 수 있나요?+
많은 워크플로에서 Oleafly는 글쓰기, 교정, 컴파일, 인용, PDF, 이력서, AI, Git 클라이언트를 각각 따로 두는 것을 대체할 수 있습니다. 일반 파일과 GitHub도 그대로 함께 쓰므로, 작업을 독점 형식에 가두지 않고도 도입할 수 있습니다.
06이미 있는 논문이나 이력서를 가져올 수 있나요?+
네. 기존 폴더를 열거나 온라인 LaTeX 에디터에서 내보낸 것을 포함해 ZIP을 가져오세요. Oleafly가 메인 문서를 찾아냅니다. 텍스트 기반 PDF는 로컬에서 LaTeX로 변환하고, DOCX는 Pandoc으로 처리하며, 스캔본이나 사진은 비전 모델로 전사합니다.
07PDF 출력이 ATS 친화적인가요?+
ATS 통과 여부는 템플릿과 내용에 따라 달라지므로 Oleafly는 점수를 보장하지 않습니다. 이력서 템플릿은 선택 가능한 Unicode 텍스트, 임베드 글꼴, 단일 단 레이아웃, 선형 읽기 순서를 사용합니다. 사전 점검이 PDF를 보내기 전에 파서가 실제로 추출하는 내용을 보여줍니다.
08공동 작업과 동기화는 어떻게 되나요?+
현재 공동 작업은 Git으로 합니다. GitHub에 게시한 뒤 Oleafly 안에서 푸시하고 풀하세요. 실시간 공동 편집, 댓글, 관리형 동기화는 계획되어 있지만 아직 앱에는 없습니다.
09오프라인에서도, AI 없이도 쓸 수 있나요?+
네. 글쓰기, 로컬 컴파일, PDF 검토, 교정은 AI 없이 동작합니다. 오프라인으로 전환하기 전에 프로젝트에 필요한 패키지, 글꼴, 도구를 내려받으세요. 로컬 AI는 Ollama에서 모델을 내려받아 로컬 서버를 연결하면 됩니다.
10내가 계속 쓰는 동안 에이전트가 작업할 수 있나요?+
네. 연구 작업을 열고 작업에 간단한 지시를 주고 에이전트를 고르세요. 에이전트가 격리된 사본에서 작업하는 동안 당신은 논문을 계속 쓰면 됩니다. 활동을 따라가고, 변경된 파일을 미리 보고, 원하는 결과만 적용하세요.
E=hν
LaTeX
\[ E = h\nu \]다운로드
무료. 오픈 소스. 당신의 것.
최신 릴리스의 프리빌드 설치 파일을 받거나 소스에서 빌드. 계정 없음, 원격 측정 없음.
Download for macOSApple SiliconDownload for Windows64-bit · MSI or EXEDownload for LinuxAppImage · DEB · RPM
일부 빌드는 처음 실행할 때 운영 체제 경고가 나타날 수 있습니다. 확인할 사항과 계속 진행하는 방법은 설치 가이드에서 설명합니다.