{"id":"W2026170849","doi":"10.1007/s10664-014-9338-4","title":"On rapid releases and software testing: a case study and a semi-systematic literature review","year":2014,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Context (archaeology); Test suite; Systematic review; Scope (computer science); Software engineering; Software; Software bug; Software testing; Test case; Operating system","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":[],"consensus_categories":[],"category_scores_codex":[0.02303179,0.0006149614,0.001146476,0.01595971,0.001666285,0.002429589,0.001555555,0.001776177,0.002354048],"category_scores_gemma":[0.06054345,0.0005362562,0.00103523,0.0151588,0.001875564,0.003771844,0.002642617,0.001166006,0.0003995851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003465379,"about_ca_system_score_gemma":0.01595458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004378614,"about_ca_topic_score_gemma":0.01370758,"domain_scores_codex":[0.9768734,0.0111823,0.004196422,0.001113187,0.005888236,0.0007464995],"domain_scores_gemma":[0.7839958,0.1880927,0.01123132,0.003712899,0.01197508,0.000992185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0004212466,0.0008285102,0.02440714,0.1423393,0.0006001983,0.01505051,0.08042626,0.001375739,0.007270369,0.01133761,0.01063186,0.7053112],"study_design_scores_gemma":[0.0001931819,0.002017755,0.09426519,0.3618445,0.002899361,0.01448214,0.2001253,0.001517544,0.01137942,0.008958283,0.3019783,0.0003391879],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.4678476,0.4406667,0.02484396,0.01048364,0.0006090443,0.00710003,0.002929332,0.0001667045,0.04535301],"genre_scores_gemma":[0.6567097,0.3082301,0.02434525,0.002848104,0.0002335793,0.002498043,0.001667849,0.0000873259,0.003379987],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02303179,"threshold_uncertainty_score":0.1218052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02742795834347492,"score_gpt":0.2857589749436667,"score_spread":0.2583310166001918,"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."}}