代码大模型 / AI 编程

An Easy to Use Repository for Comparing and Improving Machine Learning Algorithm Usage

Michael R. Smith, Andrew White, Christophe Giraud-Carrier, Tony Martinez

专题命中 仓库级理解 ：repository(title)；分类 cs.LG

Comments 7 pages, 1 figure, 6 tables

A repository of vanilla long term integrations of the Solar System

Garett Brown, Hanno Rein

专题命中 仓库级理解 ：repository(title,comments)

Comments Published in Res. Notes AAS, 3 pages, 1 figure, data repository: https://zenodo.org/record/4299102

Journal ref 2020 Res. Notes AAS 4 221

Persistent Recursive Worlds Enable Autonomous Software Evolution

持久递归世界支持自主软件演化

Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng

专题命中 仓库级理解 ：repository(abstract)；coding agent(abstract)；分类 cs.SE、cs.AI

AI总结 该研究提出 Genesis 框架，以持久递归世界替代持久智能体，成功构建 C 编译器、重实现 MESA 模块，实现长周期软件开发并获显著性能提升。

CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research

CIDR：一个大规模工业源代码数据集用于软件工程研究

Vladislav Savenkov

机构 * Fermatix AI 纠错

专题命中 仓库级理解 ：repository(abstract,abstract_cn)；分类 cs.SE、cs.AI

AI总结 CIDR是首个基于工业合作的大型源代码数据集，包含2440个仓库、138种语言和3.73亿行代码，支持代码智能、软件质量分析和语言模型预训练等研究。

Comments 60 pages, 13 figures, 8 appendices. Dataset access: https://fermatix.ai/#Contact. Anonymization tool: https://github.com/Fermatix/repo-sanitizer. Metadata utility: https://github.com/Fermatix/repo_metadata_cli

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Harness手册：使不断演进的智能体框架具有可读性、可导航性和可编辑性

Ruhan Wang, Yucheng Shi, Zongxia Li, Zhongzhi Li, Yue Yu, Junyao Yang, Kishan Panaganti, Haitao Mi, Dongruo Zhou, Leoweiliang

机构 * Tencent（腾讯） ； Indiana University（印第安纳大学） ； University of Maryland, College Park（马里兰大学帕克分校） ； University of Georgia（佐治亚大学） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 仓库级理解 ：repository(abstract)；coding agent(abstract)；分类 cs.SE、cs.AI

AI总结 研究智能体框架演进中行为定位难的问题，提出通过Harness手册和行为引导的渐进式披露，以行为为中心自动合成框架表示并辅助规划，提高行为定位和编辑计划质量，助力复杂智能体系统发展。

Comments 29 pages, 6 figures. Project page: https://ruhan-wang.github.io/Harness-Handbook/

Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code

这些暴力的愉悦会有暴力的结局吗？衡量代理代码合并后的命运

Chunqiu Steven Xia, Courtney Miller

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； George Washington University（乔治华盛顿大学） 纠错

专题命中 仓库级理解 ：repository(abstract)；coding agent(abstract)；分类 cs.SE、cs.AI

AI总结 研究代理代码合并后的命运，通过对182个仓库实证分析，发现其虽与人工维护率相似，但需更高纠正性维护率，还引入更多问题，且维护负担与仓库特征有关，强调评估设计代理工具要兼顾安全性与可维护性。

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

Ghosted Layers: 无约束激活对齐用于恢复层剪枝的LLM

Vincent-Daniel Yun, Junhyuk Jo, Sai Praneeth Karimireddy, Sunwoo Lee

机构 * University of Southern California（南加州大学） ； Inha University（inha大学） 纠错

专题命中 仓库级理解 ：repository(abstract,abstract_cn)；分类 cs.AI、cs.LG

AI总结 本文提出Ghosted Layers方法，通过无约束优化解决层剪枝后激活分布不匹配问题，提升LLM准确性和 perplexity 而不牺牲效率。

LLMs as Packagers of HPC Software

Caetano Melone, Daniel Nichols, Konstantinos Parasyris, Todd Gamblin, Harshitha Menon

机构 * Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室） 纠错

专题命中 仓库级理解 ：code generation(abstract)；repository(abstract)；分类 cs.SE、cs.AI

RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

Huacan Wang, Ziyi Ni, Shuo Zhang, Shuo Lu, Sen Hu, Ziyang He, Chen Hu, Jiaye Lin, Yifu Guo, Ronghao Chen, Xin Li, Daxin Jiang, Yuntao Du, Pin Lyu

机构 * UCAS（中国科学技术大学） ； CASIA（中国科学院自动化研究所） ； BUPT（北京邮电大学） ； PKU（北京大学） ； NUS（新加坡国立大学） ； StepFun ； THU（清华大学） ； SCNU（华南师范大学） ； USTC（中国科学技术大学） ； SDU（山东大学） 纠错

专题命中 仓库级理解 ：code generation(abstract)；repository(abstract)；分类 cs.SE、cs.AI

Comments A novel approach; Very practical

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology

Minh Huynh Nguyen, Thang Phan Chau, Phong X. Nguyen, Nghi D. Q. Bui

专题命中 仓库级理解 ：code generation(abstract)；software agent(abstract)；分类 cs.SE、cs.AI

Comments Work in progress

The NCS-Model: A seismic foundation model trained on the Norwegian repository of public data

NCS模型：基于挪威公共数据仓库的地震基础模型

Alba Ordonez, Theodor Johannes Line Forgaard, David Wade, Aina Juell Bugge, Hakon Nese, Anders Ueland Waldeland

专题命中 仓库级理解 ：repository(title)

AI总结 本文提出NCS模型，通过挪威大陆架的公开DISKOS数据库预训练，开发大规模地震基础模型，提供可扩展的3D训练方法，并量化盆地定向预训练和嵌入维度对下游解释性能的影响。

Comments 29 pages, 8 figures

When Pamplona sounds different: the soundscape transformation of San Fermin through intelligent acoustic sensors and a sound repository

当帕尔米奥的声音不同：通过智能声学传感器和声音仓库对圣费尔明节的声景转变

Amaia Sagasti, Frederic Font

专题命中 仓库级理解 ：repository(title)

AI总结 本研究利用智能声学传感器和声音仓库分析圣费尔明节期间帕尔米奥城市声景的变化，揭示了节日对城市声学环境的显著影响，并保存了独特的声学遗产。

Comments 46 pages, 27 figures

LymphAtlas- A Unified Multimodal Lymphoma Imaging Repository Delivering AI-Enhanced Diagnostic Insight

LymphAtlas- 一种统一的多模态淋巴瘤影像存储库，提供人工智能增强的诊断洞察

Jiajun Ding, Beiyao Zhu, Xiaosheng Liu, Lishen Zhang, Zhao Liu

专题命中 仓库级理解 ：repository(title)

AI总结 LymphAtlas通过整合PET与CT数据，构建高质量多模态数据集，提升淋巴瘤分割精度与临床应用价值。

Comments 12 pages,3 figures

Machine Learning in Acoustics: A Review and Open-Source Repository

Ryan A. McCarthy, You Zhang, Samuel A. Verburg, William F. Jenkins, Peter Gerstoft

机构 * Computer Engineering, University of Rochester, Rochester, NY 14627, USA ； Photonics Engineering, Technical University of Denmark, 2800 Kgs.\ Lyngby, Denmark 纠错

专题命中 仓库级理解 ：repository(title)

Comments Accepted by npj Acoustics, 22 pages, 12 figures

Development and Evaluation of the Institutionally Farmed Research On-line Repository and Management System (InFORMs) towards Knowledge-Sharing and Utilization

Billy S. Javier, Leo P. Paliuanan, Corazon T. Talamayan, James Karl A. Agpalza, Jesty S. Agoto

专题命中 仓库级理解 ：repository(title)

Comments The article is contained in 7 pages, reviewed by 3 external peer reviewers, and published by the International Journal of Computer Science and Network Security - an online journal subscribed in the Web of Science - ESCI

Journal ref published, IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.5, May 2022

ODEbase: A Repository of ODE Systems for Systems Biology

Christoph Lüders, Thomas Sturm, Ovidiu Radulescu

专题命中 仓库级理解 ：repository(title)

A highly scalable repository of waveform and vital signs data from bedside monitoring devices

Sanjay Malunjkar, Susan Weber, Somalee Datta

专题命中 仓库级理解 ：repository(title)

Comments 12 pages, 2 figures

SEMOUR: A Scripted Emotional Speech Repository for Urdu

Nimra Zaheer, Obaid Ullah Ahmad, Ammar Ahmed, Muhammad Shehryar Khan, Mudassir Shabbir

专题命中 仓库级理解 ：repository(title)

Comments accepted in CHI 2021

CoronaVis: A Real-time COVID-19 Tweets Data Analyzer and Data Repository

Md. Yasin Kabir, Sanjay Madria

专题命中 仓库级理解 ：repository(title)

Mix&Match: Towards Omitting Modelling Through In-Situ Alteration and Remixing of Model Repository Artifacts in Mixed Reality

Evgeny Stemasov, Tobias Wagner, Jan Gugenheimer, Enrico Rukzio

专题命中 仓库级理解 ：repository(title)

Comments 12 pages, 15 figures, 1 table, To appear in the Proceedings of the ACM Conference on Human Factors in Computing Systems 2020 (CHI'20)

Journal ref In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI '20). Association for Computing Machinery, New York, NY, USA, Paper 710, 1-12

Large-Scale-Exploit of GitHub Repository Metadata and Preventive Measures

David Knothe, Frederick Pietschmann

专题命中 仓库级理解 ：repository(title)

Comments Added references

SPOT: Open Source framework for scientific data repository and interactive visualization

Faruk Diblen, Jisk Attema, Rena Bakhshi, Sascha Caron, Luc Hendriks, Bob Stienen

专题命中 仓库级理解 ：repository(title)

LTL Store: Repository of LTL formulae from literature and case studies

Jan Křetínský, Tobias Meggendorfer, Salomon Sickert

专题命中 仓库级理解 ：repository(title)

Zebra-RFO - A Spectrum Repository for the Masses

Andrés Arcia-Moret

专题命中 仓库级理解 ：repository(title)

Comments 2 pages, 1 figure, presented at SenSys 2017

The Galaxy Cluster Merger Catalog: An Online Repository of Mock Observations from Simulated Galaxy Cluster Mergers

J. A. ZuHone, K. Kowalik, E. Ohman, E. Lau, D. Nagai

专题命中 仓库级理解 ：repository(title)

Comments 12 pages, 6 figures, version accepted to ApJ and with additional authors; data at http://gcmc.hub.yt

Learning Repository Adaptibility in an Agent-Based University Environment

Vanco Cabukovski, Roman Golubovski, Riste Temjanovski

专题命中 仓库级理解 ：repository(title)

Comments 14 pages 4 figures

An open access repository of images on plant health to enable the development of mobile disease diagnostics

David. P. Hughes, Marcel Salathe

专题命中 仓库级理解 ：repository(title)

Comments 11, 1 Figure, 1 table

Assessing the quality of a student-generated question repository

Simon P Bates, Ross K Galloway, Danny Homer, Jonathan Riise

专题命中 仓库级理解 ：repository(title)

Comments 24 pages, 5 figures

Growing the Digital Repository of Mathematical Formulae with Generic LaTeX Sources

Howard S. Cohl, Moritz Schubotz, Marjorie A. McClain, Bonita V. Saunders, Cherry Y. Zou, Azeem S. Mohammed, Alex A. Danoff

专题命中 仓库级理解 ：repository(title)

Comments I included an extra unrelated png file in the zip directory and it was falsely mentioned on a page 9. Previously I tried unsuccessfully to fix this. I removed the png file and now it is only 8 pages how it should be

Flexible and Extensible Digital Object and Repository Architecture (FEDORA)

Sandra Payette, Carl Lagoze

专题命中 仓库级理解 ：repository(title)

Comments European Conference on Research and Advanced Technology for Digital Libraries, Heraklion, Crete, published in Lecture Notes in Computer Science, Springer, 1998, http://www.springerlink.com/content/lcj85y9pg6ng32k6/