{"id":"W1914969610","doi":"10.1007/s10664-015-9393-5","title":"An in-depth study of the promises and perils of mining GitHub","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Software; Point (geometry); Data science; World Wide Web; Set (abstract data type); Event (particle physics); Empirical research; The Internet; Quality (philosophy)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004735464,0.0001410605,0.000253621,0.0001657319,0.00002122254,0.00003696737,0.0007526951,0.0000545548,0.000001130059],"category_scores_gemma":[0.002513944,0.0001094988,0.00003061939,0.0007739405,0.00003414457,0.0002666894,0.0003715519,0.0001893747,5.066326e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694804,"about_ca_system_score_gemma":0.00009241549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003816221,"about_ca_topic_score_gemma":0.0000123733,"domain_scores_codex":[0.9986364,0.00005753996,0.0002921181,0.0002878273,0.0004642531,0.0002618857],"domain_scores_gemma":[0.9985228,0.0006166723,0.00004922277,0.0005647362,0.00009146906,0.0001551564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004781138,0.000158065,0.9664018,0.00004411503,0.00001081245,0.00000711446,0.007090937,0.02469545,0.0002057069,0.0000108308,0.00002826904,0.001342189],"study_design_scores_gemma":[0.0005898576,0.0003766384,0.9794933,0.00006407967,0.000003803036,0.000008968999,0.0003049112,0.01791116,0.001010315,0.00001504148,0.00007484831,0.0001470959],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9569069,0.0001901046,0.04231337,0.00003113473,0.0001476757,0.0002486652,7.576984e-7,0.0001565177,0.000004916678],"genre_scores_gemma":[0.9810405,0.000001154906,0.01888078,0.00000702895,0.00002543505,0.00002119375,1.906598e-7,0.0000175597,0.000006089214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0241337,"threshold_uncertainty_score":0.4465233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05189227763191294,"score_gpt":0.3137880090306686,"score_spread":0.2618957313987556,"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."}}