You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
An advanced, unified platform for code quality, architectural metrics, and Agile analytics. Features Python AST parsing, Java static analysis (code smells), and interactive project health dashboards built with Streamlit.
app-server-migration helps in discovering the changes required to migrate the code from source server to target server and provides effort estimations in person days.
Stop estimating agent work in human weeks. agentpace measures how long coding agents actually take: P50/P80/P90 ranges from real Claude Code and Codex runs, the human part stated apart, never derived. Open CC0 dataset, zero-dependency Python CLI, agent skill.
Can a model estimate software effort from public data? A pre-registered blind test on nine open datasets — reproducible, and honest about the negative result.
From RFP to range — calibrated effort estimates (Ridge + conformal P10/P50/P90), ranked clarifying questions, budget-fit quotes, codebase risk context, and a learning loop. Agent in the Shell hackathon submission.
Experiment investigating influences software effort estimates generated by large language models, using a crossover design with 12 models and 88 specifications.
Reproducible software effort estimation workflow comparing traditional regressors, tabular foundation models, and baselines on NASA93 and China using leakage-aware preprocessing, repeated cross-validation, stability analysis, and exportable result tables/figures.
Software development process data analysis: Requesting (anonymized/aggregate) data from a filled MonetDB database and processing for analysis, prediction and visualization