RepoBench is a new benchmark with retrieval, completion, and pipeline tasks to evaluate code auto-completion systems on entire repositories instead of single files.
Mining source code repositories at massive scale using language modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Study of 362 Java projects finds MySQL and PostgreSQL dominate relational use while Redis and MongoDB lead non-relational, with frequent multi-DBM co-use and ORM mediation.
citing papers explorer
-
RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
RepoBench is a new benchmark with retrieval, completion, and pipeline tasks to evaluate code auto-completion systems on entire repositories instead of single files.
-
Analyzing the Adoption of Database Management Systems Throughout the History of Open Source Projects
Study of 362 Java projects finds MySQL and PostgreSQL dominate relational use while Redis and MongoDB lead non-relational, with frequent multi-DBM co-use and ORM mediation.