Replication Package: Same Project, Different Start -- How Contribution Events Shape Activity and Retention in Open Source

Replication package for the paper "Same Project, Different Start: How Contribution Events Shape Activity and Retention in Open Source," accepted at EASE 2026 (OSS4SG Track) This package contains the dataset and analysis scripts for a matched-cohort study comparing 2,001 event-based and 2,001 organic contributors across 330 open source projects. The study examines four contribution events (Google Summer of Code, LFX Mentorship, Hacktoberfest, 24 Pull Requests) and investigates how entry mechanism shapes activity patterns and long-term retention. Contents: Per-contributor data: core status, time-to-core, retention (survival months), activity profiles (6 dimensions), and weekly contribution index time series Analysis scripts: activity profiling, K-means clustering (12-week early engagement patterns), chi-squared and Mann-Whitney tests, Kaplan-Meier survival analysis, Cox proportional hazards, and Scott-Knott ESD ranking Pre-computed results: statistical test outputs, survival analysis results, Scott-Knott rankings See README.md for full replication instructions.