{"id":"W2727682072","doi":"10.1109/msr.2017.7","title":"Do Not Trust Build Results at Face Value - An Empirical Study of 30 Million CPAN Builds","year":2017,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Code (set theory); Empirical research; Software; Software evolution; Software engineering; Software system; Operating system; Software construction; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001189199,0.0002020488,0.000353734,0.00007946629,0.0006073668,0.0002134422,0.002113359,0.0001457769,0.00002145314],"category_scores_gemma":[0.0001946606,0.0001403019,0.0000877559,0.0001469896,0.0001131189,0.000780998,0.0009197318,0.0001520307,0.0000942273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007853183,"about_ca_system_score_gemma":0.0000607101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009177143,"about_ca_topic_score_gemma":0.0001016946,"domain_scores_codex":[0.9975493,0.0001633876,0.0005725962,0.0007654077,0.0006277113,0.0003215796],"domain_scores_gemma":[0.9958999,0.00009932453,0.000310543,0.003366065,0.0001547399,0.0001694235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001938737,0.001803732,0.9617987,0.00007192913,0.00005699713,0.00001965531,0.01339662,0.0007942574,0.0005084978,0.0003399719,0.003423884,0.01759183],"study_design_scores_gemma":[0.002344222,0.001685765,0.9664387,0.00003518009,0.00001454847,0.000009782628,0.0005152536,0.02214483,0.00438855,0.0001140848,0.001972948,0.0003361834],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906142,0.00001507274,0.005623678,0.0006442203,0.0006620306,0.0004830039,0.000007035004,0.0001678172,0.001782932],"genre_scores_gemma":[0.9966308,0.000005115679,0.002487237,0.0000969302,0.00008346193,0.00001326036,0.00000165765,0.000009087731,0.0006724354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02135057,"threshold_uncertainty_score":0.5721346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04495576005706785,"score_gpt":0.3429298480288655,"score_spread":0.2979740879717976,"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."}}