MétaCan
Menu
Back to cohort
Record W6967986681 · doi:10.5281/zenodo.13585832

Leveraging Reviewer Experience in Code Review Comment Generation

2024· article· en· W6967986681 on OpenAlexaff

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2024
Typearticle
Languageen
FieldComputer Science
TopicExpert finding and Q&A systems
Canadian institutionsUniversity of Waterloo
FundersAustralian Research Council
KeywordsCommitScripting languageCode (set theory)Set (abstract data type)AnnotationTest (biology)Replication (statistics)

Abstract

fetched live from OpenAlex

Leveraging Reviewer Experience in Code Review Comment Generation (Replication Package) This is the replication package for journal paper "Leveraging Reviewer Experience in Code Review Comment Generation". Authors Hong Yi Lin (University of Melbourne) Patanamon Thongtanunam (University of Melbourne) Christoph Treude (Singapore Management University) Michael Godfrey (University of Waterloo) Chunhua Liu (University of Melbourne) Wachiraphan Charoenwet (University of Melbourne) List of Contents Manual_Evaluation Accuracy annotations Informativeness annotations Comment category annotations Manual annotation guidelines 100 random samples ELF_AVG Model checkpoints for ELF_AVG strategy (Repository, Subsystem, Package) ELF_ACO Model checkpoints for ELF_ACO strategy (Repository, Subsystem, Package) ELF_MAX Model checkpoints for ELF_MAX strategy (Repository, Subsystem, Package) ELF_RSO Model checkpoints for ELF_RSO strategy (Repository, Subsystem, Package) Oversampling Model checkpoints for Experience-Aware Oversampling (Repository) CodeReviewer Model checkpoints for the original CodeReviewer (Fine-tuned on our dataset) Predictions All model generated predictions for test set Repository_History Pull request and commit histories for all repositories in training, validation and test set Code_Review_Dataset_Tagged Cleaned training, validation and test set including tagged ownership ratios Top10_B4_Delta Top 10 generations for each ELF model vs CodeReviewer in terms of BLEU-4 ELF_Code Fine-tuning and testing scripts for ELF (Adapted from CodeReviewer)

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.180
metaresearch head score (Gemma)0.637
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Evaluation · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.820
Threshold uncertainty score0.952

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1800.637
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0090.004
Science and technology studies0.0030.002
Scholarly communication0.0080.010
Open science0.0040.010
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0460.036

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.118
GPT teacher head0.315
Teacher spread0.196 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designObservational
DomainEvaluation
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicExpert finding and Q&A systemsFrench-language works237,207