{"id":"W2559885217","doi":"10.1007/s10664-017-9512-6","title":"Curating GitHub for engineered software projects","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":345,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Software; Classifier (UML); Software engineering; Software development; Software bug; Software metric; Data mining; Machine learning; Data science; Software quality; Artificial intelligence; Programming language","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":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006123101,0.0004914973,0.0004844389,0.0002859307,0.0008796388,0.001475019,0.002920731,0.0002454244,0.00001176359],"category_scores_gemma":[0.02884,0.0004977081,0.0002611137,0.0003506808,0.00007040808,0.001294285,0.0008799544,0.0005566725,0.00005527554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002201095,"about_ca_system_score_gemma":0.0002172112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001901792,"about_ca_topic_score_gemma":0.000002182232,"domain_scores_codex":[0.9967132,0.00002200553,0.0004611829,0.0009310645,0.0006578228,0.001214746],"domain_scores_gemma":[0.9944837,0.002630208,0.000146916,0.00205374,0.0002637099,0.0004217419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000761463,0.0004828598,0.7440752,0.002598347,0.0006419736,0.0004726692,0.004147796,0.1083505,0.002720934,0.003759247,0.02969963,0.1029747],"study_design_scores_gemma":[0.003512656,0.0006027888,0.5618833,0.0007463316,0.00005348927,0.000176656,0.00002400088,0.3276431,0.01127156,0.0008631485,0.08960683,0.003616147],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06263296,0.0002217873,0.9315885,0.0005180872,0.00130241,0.0006809021,0.00001783648,0.003022398,0.00001512463],"genre_scores_gemma":[0.4846145,0.000004651521,0.5140429,0.00008297493,0.0005319038,0.0003617467,0.00001175287,0.0001128066,0.0002368283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4219815,"threshold_uncertainty_score":0.9997475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05729360034467611,"score_gpt":0.325474775312802,"score_spread":0.2681811749681259,"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."}}