chore: update auto-revision script and documentation

Author: NoraNotDora

README.md

@@ -1,82 +1,67 @@
 # Data Analysis
-# Auto-generated from papers_raw/taxonomy.tex and papers_raw/main.bib
+# Auto-generated from taxonomy.tex and BibTeX file
 
-- short_name: "SWE-bench Verified"
-  title: "Introducing SWE-bench Verified | OpenAI"
-  authors: "OpenAI"
-  venue: "arXiv 2024"
-  year: "2024"
+- short_name: SWE-bench Verified
+  title: Introducing SWE-bench Verified | OpenAI
+  authors: OpenAI
+  year: '2024'
+  venue: '2024'
+- short_name: Patch Correctness
+  title: Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study
+  authors: You Wang, Michael Pradel, Zhongxin Liu
+  year: '2025'
+  venue: arXiv preprint arXiv:2503.15223 2025
   links:
-    arxiv: "https://openai.com/index/introducing-swe-bench-verified/"
-
-- short_name: "SWE-Bench+"
-  title: "SWE-Bench+: Enhanced Coding Benchmark for LLMs"
-  authors: "Reem Aleithan, Haoran Xue, Mohammad Mahdi Mohajer, Elijah Nnorom, Gias Uddin, Song Wang"
-  venue: "arXiv 2024"
-  year: "2024"
+    arxiv: https://arxiv.org/abs/2503.15223
+- short_name: UTBoost
+  title: 'UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench'
+  authors: Boxi Yu, Yuxuan Zhu, Pinjia He, Daniel Kang
+  year: '2025'
+  venue: arXiv preprint arXiv:2506.09289 2025
   links:
-    arxiv: "https://arxiv.org/abs/2410.06992"
-
-- short_name: "Patch Correctness"
-  title: "Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study"
-  authors: "You Wang, Michael Pradel, Zhongxin Liu"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2506.09289
+- short_name: Trustworthiness
+  title: Is Your Automated Software Engineer Trustworthy?
+  authors: Noble Saji Mathews, Meiyappan Nagappan
+  year: '2025'
+  venue: arXiv preprint arXiv:2506.17812 2025
   links:
-    arxiv: "http://arxiv.org/abs/2503.15223"
-
-- short_name: "UTBoost"
-  title: "UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench"
-  authors: "Boxi Yu, Yuxuan Zhu, Pinjia He, Daniel Kang"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2506.17812
+- short_name: Rigorous agentic benchmarks
+  title: Establishing Best Practices for Building Rigorous Agentic Benchmarks
+  authors: Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun, Andy Zhang, Shu Liu, Sasha
+    Cui, Sayash Kapoor et al.
+  year: '2025'
+  venue: arXiv preprint arXiv:2507.02825 2025
   links:
-    arxiv: "https://arxiv.org/abs/2506.09289"
-
-- short_name: "Trustworthiness"
-  title: "Is Your Automated Software Engineer Trustworthy?"
-  authors: "Noble Saji Mathews, Meiyappan Nagappan"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2507.02825
+- short_name: The SWE-Bench Illusion
+  title: 'The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason'
+  authors: Shanchao Liang, Spandan Garg, Roshanak Zilouchian Moghaddam
+  year: '2025'
+  venue: arXiv preprint arXiv:2506.12286 2025
   links:
-    arxiv: "https://arxiv.org/abs/2506.17812"
-
-- short_name: "Rigorous agentic benchmarks"
-  title: "Establishing Best Practices for Building Rigorous Agentic Benchmarks"
-  authors: "Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun, Andy Zhang, Shu Liu, Sasha Cui, Sayash Kapoor, Shayne Longpre, Kevin Meng, Rebecca Weiss, Fazl Barez, Rahul Gupta, Jwala Dhamala, Jacob Merizian, Mario Giulianelli, Harry Coppock, Cozmin Ududec, Jasjeet Sekhon, Jacob Steinhardt, Antony Kellermann, Sarah Schwettmann, Matei Zaharia, Ion Stoica, Percy Liang, Daniel Kang"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2506.12286
+- short_name: Revisiting SWE-Bench
+  title: 'Revisiting SWE-Bench: On the Importance of Data Quality for LLM-Based Code
+    Models'
+  authors: Aleithan, Reem
+  year: '2025'
+  venue: '2025 IEEE/ACM 47th International Conference on Software Engineering: Companion
+    Proceedings (ICSE-Companion) 2025'
   links:
-    arxiv: "https://arxiv.org/abs/2507.02825"
-
-- short_name: "The SWE-Bench Illusion"
-  title: "The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason"
-  authors: "Shanchao Liang, Spandan Garg, Roshanak Zilouchian Moghaddam"
-  venue: "arXiv 2025"
-  year: "2025"
+    doi: http://dx.doi.org/10.1109/ICSE-Companion66252.2025.00075
+- short_name: SPICE
+  title: "SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity,\n   \
+    \            Test Coverage, and Effort Estimation"
+  authors: Gustavo A. Oliva, Gopi Krishnan Rajbahadur, Aaditya Bhatia, Haoxiang Zhang,
+    Yihao Chen, Zhilong Chen, Arthur Leung et al.
+  year: '2025'
+  venue: ASE 2025
+- short_name: Data contamination
+  title: Does SWE-Bench-Verified Test Agent Ability or Model Memory?
+  authors: Thanosan Prathifkumar, Noble Saji Mathews, Meiyappan Nagappan
+  year: '2025'
+  venue: arXiv preprint arXiv:2512.10218 2025
   links:
-    arxiv: "https://arxiv.org/abs/2506.12286"
-
-- short_name: "Revisiting SWE-Bench"
-  title: "Revisiting SWE-Bench: On the Importance of Data Quality for LLM-Based Code Models"
-  authors: "Reem Aleithan"
-  venue: "2025 IEEE/ACM 47th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) 2025"
-  year: "2025"
-  links:
-
-- short_name: "SPICE"
-  title: "SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation"
-  authors: "Gustavo A. Oliva, Gopi Krishnan Rajbahadur, Aaditya Bhatia, Haoxiang Zhang, Yihao Chen, Zhilong Chen, Arthur Leung, Dayi Lin, Boyuan Chen, Ahmed E. Hassan"
-  venue: "arXiv 2025"
-  year: "2025"
-  links:
-    arxiv: "https://arxiv.org/abs/2507.09108"
-
-- short_name: "Data contamination"
-  title: "Does SWE-Bench-Verified Test Agent Ability or Model Memory?"
-  authors: "Thanosan Prathifkumar, Noble Saji Mathews, Meiyappan Nagappan"
-  venue: "arXiv 2025"
-  year: "2025"
-  links:
-    arxiv: "https://arxiv.org/abs/2512.10218"
-
+    arxiv: https://arxiv.org/abs/2512.10218

data/papers_data_analysis.yaml

@@ -1,51 +1,58 @@
 # Data Collection
-# Auto-generated from papers_raw/taxonomy.tex and papers_raw/main.bib
+# Auto-generated from taxonomy.tex and BibTeX file
 
-- short_name: "SWE-rebench"
-  title: "SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents"
-  authors: "Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko, Maria Trofimova, Daria Litvintseva, Boris Yangel"
-  venue: "arXiv 2025"
-  year: "2025"
+- short_name: SWE-rebench
+  title: 'SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated
+    Evaluation of Software Engineering Agents'
+  authors: Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov,
+    Simon Karasik, Andrei Andriushchenko, Maria Trofimova et al.
+  year: '2025'
+  venue: The Thirty-ninth Annual Conference on Neural Information Processing Systems
+    Datasets and Benchmarks Track 2025
   links:
-    arxiv: "https://arxiv.org/abs/2505.20411"
-
-- short_name: "RepoLaunch"
-  title: "SWE-bench Goes Live!"
-  authors: "Linghao Zhang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Chengxing Xie, Junhao Wang, Maoquan Wang, Yufan Huang, Shengyu Fu, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang"
-  venue: "arXiv 2025"
-  year: "2025"
+    openreview: https://openreview.net/forum?id=nMpJoVmRy1
+- short_name: RepoLaunch
+  title: SWE-bench Goes Live!
+  authors: Linghao Zhang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Chengxing Xie,
+    Junhao Wang et al.
+  year: '2025'
+  venue: The Thirty-ninth Annual Conference on Neural Information Processing Systems
+    Datasets and Benchmarks Track 2025
   links:
-    arxiv: "https://arxiv.org/abs/2505.23419"
-
-- short_name: "SWE-Factory"
-  title: "SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks"
-  authors: "Lianghong Guo, Yanlin Wang, Caihua Li, Pengyu Yang, Jiachi Chen, Wei Tao, Yingtian Zou, Duyu Tang, Zibin Zheng"
-  venue: "arXiv 2025"
-  year: "2025"
+    openreview: https://openreview.net/forum?id=OGWkr7gXka
+- short_name: SWE-Factory
+  title: 'SWE-Factory: Your Automated Factory for Issue Resolution Training Data and
+    Evaluation Benchmarks'
+  authors: Lianghong Guo, Yanlin Wang, Caihua Li, Wei Tao, Pengyu Yang, Jiachi Chen,
+    Haoyu Song et al.
+  year: '2025'
+  venue: arXiv preprint arXiv:2506.10954 2025
   links:
-    arxiv: "https://arxiv.org/abs/2506.10954"
-
-- short_name: "SWE-MERA"
-  title: "SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks"
-  authors: "Pavel Adamenko, Mikhail Ivanov, Aidar Valeev, Rodion Levichev, Pavel Zadorozhny, Ivan Lopatin, Dmitry Babayev, Alena Fenogenova, Valentin Malykh"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2506.10954
+- short_name: SWE-MERA
+  title: 'SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models
+    on Software Engineering Tasks'
+  authors: Pavel Adamenko, Mikhail Ivanov, Aidar Valeev, Rodion Levichev, Pavel Zadorozhny,
+    Ivan Lopatin, Dmitry Babayev et al.
+  year: '2025'
+  venue: arXiv preprint arXiv:2507.11059 2025
   links:
-    arxiv: "https://arxiv.org/abs/2507.11059"
-
-- short_name: "RepoForge"
-  title: "RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale"
-  authors: "Zhilong Chen, Chengzong Zhao, Boyuan Chen, Dayi Lin, Yihao Chen, Arthur Leung, Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Haoxiang Zhang, Aaditya Bhatia, Chong Chun Yong, Ahmed E. Hassan"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2507.11059
+- short_name: RepoForge
+  title: 'RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data
+    Curation Pipeline Synergizing SFT and RL at Scale'
+  authors: Zhilong Chen, Chengzong Zhao, Boyuan Chen, Dayi Lin, Yihao Chen, Arthur
+    Leung, Gopi Krishnan Rajbahadur et al.
+  year: '2025'
+  venue: arXiv preprint arXiv:2508.01550 2025
   links:
-    arxiv: "https://arxiv.org/abs/2508.01550"
-
-- short_name: "Multi-Docker-Eval"
-  title: "Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering"
-  authors: "Kelin Fu, Tianyu Liu, Zeyu Shang, Yingwei Ma, Jian Yang, Jiaheng Liu, Kaigui Bian"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2508.01550
+- short_name: Multi-Docker-Eval
+  title: 'Multi-Docker-Eval: A `Shovel of the Gold Rush'' Benchmark on Automatic Environment
+    Building for Software Engineering'
+  authors: Kelin Fu, Tianyu Liu, Zeyu Shang, Yingwei Ma, Jian Yang, Jiaheng Liu, Kaigui
+    Bian
+  year: '2025'
+  venue: arXiv preprint arXiv:2512.06915 2025
   links:
-    arxiv: "https://arxiv.org/abs/2512.06915"
-
+    arxiv: https://arxiv.org/abs/2512.06915

data/papers_data_collection.yaml

@@ -1,51 +1,54 @@
 # Data Synthesis
-# Auto-generated from papers_raw/taxonomy.tex and papers_raw/main.bib
+# Auto-generated from taxonomy.tex and BibTeX file
 
-- short_name: "Learn-by-interact"
-  title: "Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments"
-  authors: "Hongjin SU, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, Sercan O Arik"
-  venue: "The Thirteenth International Conference on Learning Representations 2025"
-  year: "2025"
+- short_name: Learn-by-interact
+  title: 'Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in
+    Realistic Environments'
+  authors: Hongjin SU, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, Sercan O Arik
+  year: '2025'
+  venue: The Thirteenth International Conference on Learning Representations 2025
   links:
-    arxiv: "https://openreview.net/forum?id=3UKOzGWCVY"
-
-- short_name: "R2E-Gym"
-  title: "R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents"
-  authors: "Naman Jain, Jaskirat Singh, Manish Shetty, Liang Zheng, Koushik Sen, Ion Stoica"
-  venue: "arXiv 2025"
-  year: "2025"
+    openreview: https://openreview.net/forum?id=3UKOzGWCVY
+- short_name: R2E-Gym
+  title: 'R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling
+    Open-Weights SWE Agents'
+  authors: Naman Jain, Jaskirat Singh, Manish Shetty, Tianjun Zhang, Liang Zheng,
+    Koushik Sen, Ion Stoica
+  year: '2025'
+  venue: Second Conference on Language Modeling 2025
   links:
-    arxiv: "https://arxiv.org/abs/2504.07164"
-
-- short_name: "SWE-Synth"
-  title: "SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs"
-  authors: "Minh V. T. Pham, Huy N. Phan, Hoang N. Phan, Cuong Le Chi, Tien N. Nguyen, Nghi D. Q. Bui"
-  venue: "arXiv 2025"
-  year: "2025"
+    openreview: https://openreview.net/forum?id=7evvwwdo3z
+- short_name: SWE-Synth
+  title: 'SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language
+    Models in Resolving Real-World Bugs'
+  authors: Minh V. T. Pham, Huy N. Phan, Hoang N. Phan, Cuong Le Chi, Tien N. Nguyen,
+    Nghi D. Q. Bui
+  year: '2025'
+  venue: arXiv preprint arXiv:2504.14757 2025
   links:
-    arxiv: "https://arxiv.org/abs/2504.14757"
-
-- short_name: "SWE-smith"
-  title: "SWE-smith: Scaling Data for Software Engineering Agents"
-  authors: "John Yang, Kilian Lieret, Carlos E. Jimenez, Alexander Wettig, Kabir Khandpur, Yanzhe Zhang, Binyuan Hui, Ofir Press, Ludwig Schmidt, Diyi Yang"
-  venue: "arXiv 2025"
-  year: "2025"
+    arxiv: https://arxiv.org/abs/2504.14757
+- short_name: SWE-smith
+  title: 'SWE-smith: Scaling Data for Software Engineering Agents'
+  authors: John Yang, Kilian Lieret, Carlos E Jimenez, Alexander Wettig, Kabir Khandpur,
+    Yanzhe Zhang, Binyuan Hui et al.
+  year: '2025'
+  venue: The Thirty-ninth Annual Conference on Neural Information Processing Systems
+    Datasets and Benchmarks Track 2025
   links:
-    arxiv: "https://arxiv.org/abs/2504.21798"
-
-- short_name: "SWE-Flow"
-  title: "SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner"
-  authors: "Lei Zhang, Jiaxi Yang, Min Yang, Jian Yang, Mouxiang Chen, Jiajun Zhang, Zeyu Cui, Binyuan Hui, Junyang Lin"
-  venue: "arXiv 2025"
-  year: "2025"
+    openreview: https://openreview.net/forum?id=63iVrXc8cC
+- short_name: SWE-Flow
+  title: Synthesizing Software Engineering Data in a Test-Driven Manner
+  authors: Lei Zhang, Jiaxi Yang, Min Yang, Jian Yang, Mouxiang Chen, Jiajun Zhang,
+    Zeyu Cui et al.
+  year: '2025'
+  venue: Forty-second International Conference on Machine Learning 2025
   links:
-    arxiv: "https://arxiv.org/abs/2506.09003"
-
-- short_name: "SWE-Mirror"
-  title: "SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories"
-  authors: "Junhao Wang, Daoguang Zan, Shulin Xin, Siyao Liu, Yurong Wu, Kai Shen"
-  venue: "arXiv 2025"
-  year: "2025"
+    openreview: https://openreview.net/forum?id=P9DQ2IExgS
+- short_name: SWE-Mirror
+  title: 'SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across
+    Repositories'
+  authors: Junhao Wang, Daoguang Zan, Shulin Xin, Siyao Liu, Yurong Wu, Kai Shen
+  year: '2025'
+  venue: arXiv preprint arXiv:2509.08724 2025
   links:
-    arxiv: "https://arxiv.org/abs/2509.08724"
-
+    arxiv: https://arxiv.org/abs/2509.08724