{"id":"W2401028838","doi":"10.1145/2901739.2903493","title":"Judging a commit by its cover","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Commit; Computer science; Proxy (statistics); Code (set theory); Source code; Entropy (arrow of time); Programming language; Computer security; Database; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005414511,0.0006104963,0.0005904495,0.005384752,0.0008105858,0.002050405,0.0005978137,0.001012226,0.002311582],"category_scores_gemma":[0.08777857,0.0003126155,0.0003297972,0.002766258,0.0007665955,0.002752323,0.002186753,0.001086575,0.001307753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005525137,"about_ca_system_score_gemma":0.0007667011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002240658,"about_ca_topic_score_gemma":0.004388489,"domain_scores_codex":[0.9936416,0.001061986,0.0007583728,0.0007355963,0.003430064,0.0003724936],"domain_scores_gemma":[0.9169647,0.04597702,0.01029206,0.006283829,0.01771809,0.002764359],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001395495,0.0001659707,0.6725234,0.000710891,0.0002399016,0.000494167,0.004432338,0.008453177,0.02650477,0.003999339,0.01585969,0.2652208],"study_design_scores_gemma":[0.00006231189,0.0008554997,0.7695021,0.0002607154,0.0001714312,0.001156371,0.004608212,0.1637428,0.02318313,0.01041272,0.02582226,0.0002224698],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9495028,0.000533958,0.03613009,0.0006438966,0.0002245882,0.0001733744,0.002815084,0.001562182,0.008414125],"genre_scores_gemma":[0.9792572,0.0001211402,0.01554924,0.00008783362,0.0001198239,0.00008641806,0.003155225,0.0002520757,0.001371085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9945855,"threshold_uncertainty_score":0.02863503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0149585933812961,"score_gpt":0.2481929661559607,"score_spread":0.2332343727746646,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}