Online Appendix and Replication Package – Empirical Evaluation of Open Source Large Language Models for Paper Selection (SANER 2026)

This dataset provides comprehensive supplementary materials for the paper "Empirical Evaluation of Open Source Large Language Models for Paper Selection: Are LLMs Trustworthy Tools for Scoping Reviews?" submitted to SANER 2026.It includes complete keyword lists, venue selections, inclusion criteria, raw data, analysis scripts, and validation results for multiple large language models (GPT-4.1, Mistral v2 7B, and Llama 3.3 70B) across three domains: program slicing, reactive programming, and software engineering.Sensitive information such as API keys, .env files, and private logs has been excluded. License: MITKeywords: Large Language Models, Open-Source AI, Paper Screening, Scoping Reviews, Software Engineering, Replication Package