Tootfinder

RepoSummary: Feature-Oriented Summarization and Documentation Generation for Code Repositories
Yifeng Zhu, Xianlin Zhao, Xutian Li, Yanzhen Zou, Haizhuo Yuan, Yue Wang, Bing Xie
https://arxiv.org/abs/2510.11039

RepoSummary: Feature-Oriented Summarization and Documentation Generation for Code Repositories
Repository summarization is a crucial research question in development and maintenance for software engineering. Existing repository summarization techniques primarily focus on summarizing code according to the directory tree, which is insufficient for tracing high-level features to the methods that collaboratively implement them. To address these limitations, we propose RepoSummary, a feature-oriented code repository summarization approach that simultaneously generates repository documentation…

#MySQL Repository Analysis Reveals Declining Development and Shrinking Contributor Base
https://www.infoq.com/news/2025/12/mysql-declining-development/

runme.org was a software art repository I made with Amy Alexander, Olga Goriunova and Alexei Shulgin, launched in early 2003 https://runme.org/
It came from the software art scene mainly defined by the "readme" events, including the readme/runme/dorkbot city camp

As Cyber Threats Escalate, the National Vulnerability Database Is Falling Behind
The National Institute of Standards and Technology (NIST) is struggling.
It faces a growing backlog to process data in its vulnerability repository, which publicly shares information assessing and detailing mitigation solutions against new cyber exploits.
With nearly 1,800 new reported vulnerabilities sitting in a queue for analysis this year, delays in processing leave the United States increa…

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Xu Yang, Jiayuan Zhou, Michael Pacheco, Wenhan Zhu, Pengfei He, Shaowei Wang, Kui Liu, Ruiqi Pan
https://arxiv.org/abs/2510.11838

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, repository-level issue resolution. Existing agent-based methods have two key limitations. First, they lack of procedural knowledge (i.e., how an issue is fixed step-by-step and rationales behind it) to learn and leverage for issue resolution. Second, they rely on massive computational power to blindly explore the solution sp…

New on blog: "How we incidentally uncovered a 7-year old bug in gentoo-ci"
"""
“Gentoo CI” is the service providing periodic linting for the Gentoo repository. It is a part of the Repository mirror and CI project that I’ve started in 2015. Of course, it all started as a temporary third-party solution, but it persisted, was integrated into Gentoo Infrastructure and grew organically into quite a monstrosity.
It’s imperfect in many ways. In particular, it has only some degree of error recovery and when things go wrong beyond that, it requires a manual fix. Often the “fix” is to stop mirroring a problematic repository. Over time, I’ve started having serious doubts about the project, and proposed sunsetting most of it.
Lately, things have been getting worse. What started as a minor change in behavior of Git triggered a whole cascade of failures, leading to me finally announcing the deadline for sunsetting the mirroring of third-party repositories, and starting ripping non-critical bits out of it. Interesting enough, this whole process led me to finally discover the root cause of most of these failures — a bug that has existed since the very early version of the code, but happened to be hidden by the hacky error recovery code. Here’s the story of it.
"""
#Gentoo

Slowly starting down a bit of a rabbit hole, even though I really don't have time between work, school, and everything that needs done at the new house.
Since taking my first college math course a while ago, I've been taking notes in a combination of Markdown and LaTex for the equations. At first I was just checking my notes into a Forgejo repository, and viewing them via browser. Then we moved, the computer hosting some of my home services suddenly failed, and I realized I wan…

I was looking into the #DANDI archive, following a post of @… that mentioned it as a possibility for #Neuroscience data storage.. It looks like it could be useful i…

TALP-Pages: An easy-to-integrate continuous performance monitoring framework
Valentin Seitz, Jordy Trilaksono, Marta Garcia-Gasulla
https://arxiv.org/abs/2510.12436 https://

TALP-Pages: An easy-to-integrate continuous performance monitoring framework
Ensuring good performance is a key aspect in the development of codes that target HPC machines. As these codes are under active development, the necessity to detect performance degradation early in the development process becomes apparent. In addition, having meaningful insight into application scaling behavior tightly coupled to the development workflow is helpful. In this paper, we introduce TALP-Pages, an easy-to-integrate framework that enables developers to get fast and in-repository feedb…

Researchers report rare intrusion by suspected Chinese hackers into Russian tech firm https://therecord.media/rare-china-linked-intrusion-russian-tech-firms

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
Kostiantyn Bevziuk, Andrii Fatula, Svetozar Lashin Yaroslav Opanasenko, Anna Tukhtarova, Ashok Jallepalli Pradeepkumar Sharma, Hritvik Shrivastava
https://arxiv.org/abs/2510.08876

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure, capturing semantic relationships and allowing a significant level of automatization of further repository development. The graph encodes syntactic relations such as containment, implementation, references, calls, and inheritance, and augments nodes with LLM-derived summaries and vector embeddings. A hybrid retrieval …

»Syncthing‑Fork unter fremder Kontrolle? Community schluckt das nicht:
Das Repository des beliebten Syncthing-Forks für Android verschwand von GitHub und taucht unter zwielichten Umständen wieder auf – ist das ein Open-Source-Hack?«
Mist, nun muss ich gucken ob die @… Variante vom @…

Syncthing‑Fork unter fremder Kontrolle? Community schluckt das nicht
Das Repository des beliebten Syncthing-Forks für Android verschwand von GitHub und taucht unter zwielichten Umständen wieder auf – ist das ein Open-Source-Hack?

Evidence of Physiological Co-Modulation During Human-Animal Interaction: A Systematic Review
G. Bargigli, L. Frassineti, A. Lanata', P. Baragli, C. Scopa, A. Vignoli
https://arxiv.org/abs/2510.10559

Evidence of Physiological Co-Modulation During Human-Animal Interaction: A Systematic Review
This review examines the evidence in the literature for physiological co-modulation during human-animal interaction. The aim of this work is to identify studies that assessed co-modulation via simultaneous measurement of physiological signals in both species, performing quantitative comparisons, and evaluate the consistency of the findings.\\ We searched PubMed, EM-BASE, Scopus, Google Scholar, Animal Studies Repository, and the ''Consensus app'' tool between June and August 2025 (last search: …

@… @… I would argue it’s not at all undesirable when done sensibly: It’s called libraries.
You can put a library in one repository, the app in another, and at build time you combine both into one application.

Repository-Aware File Path Retrieval via Fine-Tuned LLMs
Vasudha Yanuganti, Ishaan Puri, Swapnil Chhatre, Mantinder Singh, Ashok Jallepalli, Hritvik Shrivastava, Pradeep Kumar Sharma
https://arxiv.org/abs/2510.08850

Repository-Aware File Path Retrieval via Fine-Tuned LLMs
Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the bug introduced?" Traditional code search (keyword or IR based) often misses semantic context and cross file links, while large language models (LLMs) understand natural language but lack repository specific detail. We present a method for file path retrieval that fine tunes a strong LLM (Qwen3-8B) with QLoRA and Unslot…

(PhD thesis, 2024) Prototyping phosphene vision: Simulation-based optimization of visual neuroprosthetics using deep learning #BCI

Oh yeah, totally looks legit... especially that URL!
😂

"How Fanfiction Can Help Us Reimagine Scholarly Publishing"
https://doi.org/10.1146/katina-102825-1
"Archive of Our Own, a digital fanfiction repository, shows what’s possible when we design our infrastructures around the communities that use them, rather than around extractive…

Panicked message from the boss. Looks like one of the documentation files is corrupted. We haven't had the time to cross train that process. Too many manual steps to extract the information from the repository, download to the network work folder, import into Word format, locate specific items and run the macro to format those, export to PDF and then reindex the production doc folder with the change.

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion
Sheng Zhang, Yifan Ding, Shuquan Lian, Shun Song, Hui Li
https://arxiv.org/abs/2509.16112

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion
Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository. Recent strides in Code Large Language Models (code LLMs) have spurred the development of repository-level code completion methods, yielding promising results. Nevertheless, they suffer from issues such as inappropriate query construction, single-path code retrieval, and misalignment between code retriever and code LLM. To address these problems, we introduce CodeRAG,…

@… @… Is the repository private? Or is the user of this repository private? If you can access the repository from a private tab then it shouldn't be asking for credentials.

i love how apt tells me
N: This must be accepted explicitly before updates for this repository can be applied. See apt-secure(8) manpage for details.
but the fuckin manpage does not tell you how to accept anything explicitly. it does not even have the word "accept" in it

Cryogenic Materials Repository: A Public Resource and New Measurements for Cryogenic Research Applications
Henry E. Nachman (Department of Physics, The University of Texas at Austin, Weinberg Institute for Theoretical Physics, Texas Center for Cosmology and Astroparticle Physics, Austin, TX, USA), Oorie Desai (Department of Physics, The University of Texas at Austin, Weinberg Institute for Theoretical Physics, Texas Center for Cosmology and Astroparticle Physics, Austin, TX, USA), Nich…

Cryogenic Materials Repository: A Public Resource and New Measurements for Cryogenic Research Applications
Low-temperature systems play a vital role in a variety of scientific research applications, including the next generation of cosmology and astrophysics telescopes. More ambitious cryogenic applications require precise estimates of the thermal conductivity of materials and thermal joints to meet project goals. We present the development of the Cryogenic Material Repository (CMR), a public GitHub repository of cryogenic material properties data created to support and enable researchers across sci…

As a security precaution I had previously configured every single 11ty repository to have its own single-package-scoped npm token (there were probably ~30 or so), so this is a lovely improvement 😅

“By 2040, the Locational scenario could reduce the total system cost by 23 – 59 Bn. EUR annually. These savings are in the order of magnitude of those associated with the integration of European electricity markets.”
https://publications.jrc.ec.europa.eu/repository/handle/J…

Locational Price Signals in Europe
As Europe strives to become the first climate neutral continent, grid congestion is becoming an increasingly urgent issue, with the potential to lead to large-scale curtailment of renewables and undermine the system’s security. Accordingly, the Mission Letter to Commissioner for Energy and Affordable Housing Dan Jørgensen lists the task to improve locational price signals. These aim to ensure that investments occur where they are most beneficial to the system, while incentivizing an efficien…

Matz steals code so we steal code
(these repositories were stolen from their maintainers by Ruby Central)
https://www.ruby-lang.org/en/news/2025/10/17/rubygems-repository-transition/

F-Droid and Google's Developer Registration Decree https://f-droid.org/en/2025/09/29/google-developer-registration-decree.html
"(...) the developer registration decree will end the F-Droid project and other free/open-source app distribution sou…

BTW #docker #dockerdown

I think I have a whole blog post/talk/video in me on this topic, but I feel like most ppl lack imagination when thinking about the DB repository pattern. It doesn't have to be just add/list/get—it's probably even wasteful!
Catchy: ”Database Repository Pattern for People Who Don't Hate Databases”

"Interesting that Lloyd suggests that Andrew should be “packed out to a shed in the Outer Hebrides”. Why is Scotland always seen as the repository for unwanted goods and people?" — @…
A council house in Clacton would seem more suitable. I'm sure he would be welcome there.

IRS Direct File is open source
Here's it's repository https://c.im/@cdarwin/115494776208277993

Falschinformationen können dazu führen, dass Klimaschutzmaßnahmen gezielt untergraben werden. Journalisten greifen daher häufig zu der Strategie, solche Falschinformationen direkt zu widerlegen. Forschungsergebnisse zeigen jedoch, dass diese auf den ersten Blick plausible Vorgehensweise nicht in allen Fällen wirksam ist. Unter bestimmten Bedingungen kann sie unbeabsichtigt sogar zur weiteren Verbreitung von Falschinformationen beitragen.

#Axum Backend Series: Models, Migration, DTOs and Repository Pattern
https://blog.0xshadow.dev/posts/backend-engineering-with-axum/axum-model-setup/

Microsoft: “Managers are lame, we need emperors.”

github.com/microsoft/terminal/blob/main/src/cascadia/WindowsTerminal/WindowEmperor.h

terminal/src/cascadia/WindowsTerminal/WindowEmperor.h at main · microsoft/terminal · GitHub
The new Windows Terminal and the original Windows console host, all in the same place! - terminal/src/cascadia/WindowsTerminal/WindowEmperor.h at main · microsoft/terminal

Improving Code Localization with Repository Memory
Boshi Wang, Weijian Xu, Yunsheng Li, Mei Gao, Yujia Xie, Huan Sun, Dongdong Chen
https://arxiv.org/abs/2510.01003 https://

Improving Code Localization with Repository Memory
Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from the repository, they overlook the critical aspect of memory, where each instance is typically handled from scratch assuming no prior repository knowledge. In contrast, human developers naturally build long-term repository memory, such as the functionality of key modules and assoc…

I gave a talk at SCD today, thanks for attending and for the good feedback - if you have more questions, keep them coming.
Until then, here are the slides and a link to the repository with the config.
https://winkelwagen.de/2025/09/16/deploying-shopwa…

check out how quickly #GitPages (and #Grebedoc) can check out a giant git repository without any changes!
if supported by the server, it retrieves only a single tree from git (no other branches, no tags, no history, no file contents), backfills it from the existing site contents, and then p…

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang
https://arxiv.org/abs/2509.16198

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies pr…

With a FreeBSD pkg repository configuration file set to use quarterly for the one and only repo:
― why is latest (not quarterly) used for bootstrapping?
https://gist.github.com/grahamperrin/1a36d21e9c6d3bc363cee7ecfe779595#file-2…

Microsoft blocks Israel’s use of its technology in mass surveillance of Palestinians | Israel | The Guardian
https://www.theguardian.com/world/2025/sep/25/microsoft-blocks-israels-use-of-its-technology-in-mass-s…

If you are still using javax.mail.jar 1.x aka #JavaMail be aware that this is not supported any more. As a quick fix you can use the 1.6.8 release of jakarta.mail
https://mvnrepository.com/artifact/com

I found a curious document in the archives and followed it down a rabbit hole. The internet's great for this, but it has its limits - sometimes we need to sit down with a collection that hasn't been digitized and put online. So I located the local repository that's liable to have the most complete collection, thinking I'd write them an email inquiry... Only to find they only have a phone number! Now I want to visit even more.

#emacs users who bank with the uk starling bank, (niche!): I received a handy new contribution to my starling.el project, a new view that lets you see your spending insights. Thanks to Alex:
https://github.com/draxil/starling-e…

Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches
Yicheng Tao, Yao Qin, Yepang Liu
https://arxiv.org/abs/2510.04905 https://

Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches
Recent advancements in large language models (LLMs) have substantially improved automated code generation. While function-level and file-level generation have achieved promising results, real-world software development typically requires reasoning across entire repositories. This gives rise to the challenging task of Repository-Level Code Generation (RLCG), where models must capture long-range dependencies, ensure global semantic consistency, and generate coherent code spanning multiple files o…

Early Look at Maine Primary Races: Platner Leads Mills, Collins Far Ahead of Unknown GOP Challengers 10/23/2025 (University of New Hampshire Scholars Repository)
https://scholars.unh.edu/survey_center_polls/897/
http://www.memeorandum.com/251023/p51#a251023p51

Is it actually possible to delete files from a git repository without breaking existing forks etc?
There's a load of large generated and audio in @…'s git history. Trying to wipe them from history seems super risky though..

GLAMs and humanities folk deserve better AI models, number 5654 in a series: 'the subjectivity of a task or instance negatively affects the performance of a model – an observation that is particularly worrying for humanities research'.
From Kaspar Beelen's report, Small Language Models for libraries and computational humanities

Registration is now open for the San Jose State University Biennial Open Access Conference (free and online), which has as its theme "Defend Research, Defend Open Access." Catherine Mitchell and I will be providing the keynote to launch a day of sessions exploring "the growing threats to academic freedom, research infrastructure, and equitable access to knowledge in politically volatile times."

My GitHub notifications now look like this every few days 😅
Random bots keep creating repos (not forked) and one of the commits mention me.
Original repo and commit here: https://github.com/matiassingers/awesome-readme/commit/4130eb071cf…

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
Pratik Shah, Rajat Ghosh, Aryan Singhal, Debojyoti Dutta

If you or your colleagues have ROAs in the #AFRINIC #RPKI repository, see this email from @…
Those with a non-conformant subject name can reissue the ROA themselves, the other…

»You already have a git server:
If you have a git repository on a server with ssh access, you can just clone it.«
Actually, this is only logical and correspondingly simple, but you should also use this. Now I came across this with the help of a link to this guide.
🧑‍💻 https://maurycyz.com/misc/easy_git/

@… oh, wild. is WPEngine using their own plugin repository now or are they still tied to the centralized one?

An Artificial Intelligence Driven Semantic Similarity-Based Pipeline for Rapid Literature
Abhiyan Dhakal (Kathmandu University, Dhulikhel, Nepal), Kausik Paudel (Kathmandu University, Dhulikhel, Nepal), Sanjog Sigdel (Kathmandu University, Dhulikhel, Nepal)
https://arxiv.org/abs/2509.15292

An Artificial Intelligence Driven Semantic Similarity-Based Pipeline for Rapid Literature
We propose an automated pipeline for performing literature reviews using semantic similarity. Unlike traditional systematic review systems or optimization based methods, this work emphasizes minimal overhead and high relevance by using transformer based embeddings and cosine similarity. By providing a paper title and abstract, it generates relevant keywords, fetches relevant papers from open access repository, and ranks them based on their semantic closeness to the input. Three embedding models…

Who Do You Think You Are? Creating RSE Personas from GitHub Interactions
Felicity Anderson, Julien Sindt, Neil Chue Hong
https://arxiv.org/abs/2510.05390 https://

Who Do You Think You Are? Creating RSE Personas from GitHub Interactions
We describe data-driven RSE personas: an approach combining software repository mining and data-driven personas applied to research software (RS), an attempt to describe and identify common and rare patterns of Research Software Engineering (RSE) development. This allows individuals and RS project teams to understand their contributions, impact and repository dynamics - an important foundation for improving RSE. We evaluate the method on different patterns of collaborative interaction behaviour…

#noteToSelf: Nächstes Mal für die online #Personalausweis Funktion:
- neuste #AusweisApp von :fdroid: #FDroid

AusweisApp | F-Droid - Free and Open Source Android App Repository
Personalausweis mit dem Handy nutzen

maybe i should have a website again
i've avoided it for years after deciding that i didn't like both the nature of my old writing and the reasons for writing
but i've worked on a lot of different things, and a lot of those are useful, and maybe it's good for there to be some unified repository of them that adds context

arXiv Changes Rules After Getting Spammed With AI-Generated 'Research' Papers https://www.404media.co/arxiv-changes-rules-after-getting-spammed-with-ai-generated-research-papers/

@…
# pkg-static -o ABI=FreeBSD:15:(sysctl -n hw.machine_arch) upgrade -yr FreeBSD-base
The --yes might be very risky in some cases.
Prior use of bectl(8) was sane …
Removals of non-base packages for installations, or upgrades, that specify the FreeBSD-base repository alone · Issue #2414 · freebsd/pkg
― <

Prompt Commons: Collective Prompting as Governance for Urban AI
Rashid Mushkani
https://arxiv.org/abs/2509.12415 https://arxiv.org/pdf/2509.12415

Prompt Commons: Collective Prompting as Governance for Urban AI
Large Language Models (LLMs) are entering urban governance, yet their outputs are highly sensitive to prompts that carry value judgments. We propose Prompt Commons - a versioned, community-maintained repository of prompts with governance metadata, licensing, and moderation - to steer model behaviour toward pluralism. Using a Montreal dataset (443 human prompts; 3,317 after augmentation), we pilot three governance states (open, curated, veto-enabled). On a contested policy benchmark, a single-au…

A Systematic Review of FAIR-compliant Big Data Software Reference Architectures
Jo\~ao Pedro de Carvalho Castro, Maria J\'ulia Soares De Grandi, Cristina Dutra de Aguiar
https://arxiv.org/abs/2509.14370

A Systematic Review of FAIR-compliant Big Data Software Reference Architectures
To meet the standards of the Open Science movement, the FAIR Principles emphasize the importance of making scientific data Findable, Accessible, Interoperable, and Reusable. Yet, creating a repository that adheres to these principles presents significant challenges. Managing large volumes of diverse research data and metadata, often generated rapidly, requires a precise approach. This necessity has led to the development of Software Reference Architectures (SRAs) to guide the implementation pro…

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Junting Pan, Mingjie Zhan, Hongsheng Li
https://arxiv.org/abs/2509.22644

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and user-interaction feedback, current code agents rely only on simple code execution for feedback and verification. This approach fails to capture the actual quality of the generated code. In this paper, we propose WebGen-Agent, a novel website-generation agent tha…

Be part of the conversation about how to #DefendResearch, support #OpenAccess, and protect #Education! Register for next week's SJSU OA Virtual Conference, where I'm very excited …

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
Pratik Shah, Rajat Ghosh, Aryan Singhal, Debojyoti Dutta
https://arxiv.org/abs/2509.25257 https://

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code entity queries (for example, locating a specific class or retrieving the dependencies of a function), as well as general queries without explicit code entities, or natural language queries (for example, describing a task and retrieving the corresponding code…

#TIL that #Gitolite can't handle repositories with different default branch names. As in, if you push a "main" branch into a "master" server, you get no HEAD 🤦. And you can only change that via SSH-ing to the server and modifying the underlying repository.
Apparently, you could also install a hook to automatically fix HEAD for you: #Gentoo #git

We and our 26 submodules are requesting permission to ...

Towards Repository-Level Program Verification with Large Language Models
Si Cheng Zhong, Xujie Si
https://arxiv.org/abs/2509.25197 https://arxiv.org/pdf/25…

Towards Repository-Level Program Verification with Large Language Models
Recent advancements in large language models (LLMs) suggest great promises in code and proof generations. However, scaling automated formal verification to real-world projects requires resolving cross-module dependencies and global contexts, which are crucial challenges overlooked by existing LLM-based methods with a special focus on targeting isolated, function-level verification tasks. To systematically explore and address the significant challenges of verifying entire software repositories, …

Beyond More Context: How Granularity and Order Drive Code Completion Quality
Uswat Yusuf, Genevieve Caumartin, Diego Elias Costa
https://arxiv.org/abs/2510.06606 https://…

Beyond More Context: How Granularity and Order Drive Code Completion Quality
Context plays an important role in the quality of code completion, as Large Language Models (LLMs) require sufficient and relevant information to assist developers in code generation tasks. However, composing a relevant context for code completion poses challenges in large repositories: First, the limited context length of LLMs makes it impractical to include all repository files. Second, the quality of generated code is highly sensitive to noisy or irrelevant context. In this paper, we present…

The #fdroid app #Coffee keeps your screen awake when you ie. dislike having to constantly unlock it.
https://f-droid.org/en/…

Coffee | F-Droid - Free and Open Source Android App Repository
Keep display awake

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
Jos\'e Cambronero, Michele Tufano, Sherry Shi, Renyao Wei, Grant Uy, Runxiang Cheng, Chin-Jung Liu, Shiying Pan, Satish Chandra, Pat Rondon
https://arxiv.org/abs/2510.03217

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
Agentic Automated Program Repair (APR) is increasingly tackling complex, repository-level bugs in industry, but ultimately agent-generated patches still need to be reviewed by a human before committing them to ensure they address the bug. Showing unlikely patches to developers can lead to substantial noise, wasting valuable developer time and eroding trust in automated code changes. We introduce two complementary LLM-based policies to reduce such noise: bug abstention and patch validation polic…

MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand, Joey Dodds, Daniel Kroening
https://arxiv.org/abs/2509.16187

MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
Code translation transforms source code from one programming language (PL) to another. Validating the functional equivalence of translation and repairing, if necessary, are critical steps in code translation. Existing automated validation and repair approaches struggle to generalize to many PLs due to high engineering overhead, and they rely on existing and often inadequate test suites, which results in false claims of equivalence and ineffective translation repair. We develop MatchFixAgent, a …

Replaced article(s) found for cs.SE. https://arxiv.org/list/cs.SE/new
[1/1]:
- Synergizing LLMs and Knowledge Graphs: A Novel Approach to Software Repository-Related Question A...
Samuel Abedu, SayedHassan Khatoonabadi, Emad Shihab

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
Chengran Yang, Ting Zhang, Jinfeng Jiang, Xin Zhou, Haoye Tian, Jieke Shi, Junkai Chen, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, David Lo
https://arxiv.org/abs/2510.01002

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis reveals three fundamental weaknesses in state-of-the-art AVR approaches: (1) limited cross-repository generalization, with performance drops on unseen codebases; (2) inability to capture long-range dependencies, causing a performance degradation on complex, multi-hunk repairs; and (3) over-reliance on superficial lexical p…

A New Benchmark for Evaluating Code Translation with Third-Party Libraries
Pengyu Xue, Kunwu Zheng, Zhen Yang, Yifei Pei, Linhao Wu, Jiahui Dong, Xiapu Luo, Yan Xiao, Fei Liu, Yuxuan Zhang, Xiran Lyu, Xianhang Li, Xuanyu Zhu, Chengyi Wang
https://arxiv.org/abs/2509.12087

A New Benchmark for Evaluating Code Translation with Third-Party Libraries
In recent years, Large Language Models (LLMs) have been widely studied in the code translation field on the method, class, and even repository levels. However, most of these benchmarks are limited in terms of Third-Party Library (TPL) categories and scales, making TPL-related errors hard to expose and hindering the development of targeted solutions. Considering the high dependence (over 90%) on TPLs in practical programming, demystifying and analyzing LLMs' code translation performance involvin…

CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects
Hanyang Guo, Xunjin Zheng, Zihan Liao, Hang Yu, Peng DI, Ziyin Zhang, Hong-Ning Dai
https://arxiv.org/abs/2509.14856

CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects
Automated code review (CR) is a key application for Large Language Models (LLMs), but progress is hampered by a "reality gap": existing benchmarks evaluate models on isolated sub-tasks using simplified, context-poor data. This fails to reflect the holistic context-rich nature of real-world CR. To bridge this gap, we introduce CodeFuse-CR-Bench, the first comprehensiveness-aware benchmark for repository-level CR evaluation. CodeFuse-CR-Bench comprises 601 high-quality instances from 70 Python pr…

Crash Report Enhancement with Large Language Models: An Empirical Study
S M Farah Al Fahim (Peter), Md Nakhla Rafi (Peter), Zeyang Ma (Peter), Dong Jae Kim (Peter), Tse-Hsun (Peter), Chen
https://arxiv.org/abs/2509.13535

Crash Report Enhancement with Large Language Models: An Empirical Study
Crash reports are central to software maintenance, yet many lack the diagnostic detail developers need to debug efficiently. We examine whether large language models can enhance crash reports by adding fault locations, root-cause explanations, and repair suggestions. We study two enhancement strategies: Direct-LLM, a single-shot approach that uses stack-trace context, and Agentic-LLM, an iterative approach that explores the repository for additional evidence. On a dataset of 492 real-world cras…