{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001026332,0.000448234,0.0006997797,0.0002873302,0.0001689825,0.0003624868,0.0004812675,0.0001213308,0.000003618791],"category_scores_gemma":[0.03957811,0.0003768664,0.00007158864,0.001287038,0.0000298482,0.0003317526,0.0004650722,0.0006187606,0.00001179168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007153599,"about_ca_system_score_gemma":0.00003296275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001006421,"about_ca_topic_score_gemma":0.000001105087,"domain_scores_codex":[0.9973565,0.0002009169,0.0004872451,0.00083498,0.0005679707,0.0005523801],"domain_scores_gemma":[0.9886906,0.009689499,0.00008116692,0.0009313963,0.0001627888,0.0004445104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0000361614,0.001500013,0.4140809,0.4414271,0.0006947088,0.03331838,0.01018986,0.007679637,0.00006732767,0.0003842,0.009574081,0.08104759],"study_design_scores_gemma":[0.00710534,0.01025711,0.1406277,0.4322082,0.0006936993,0.08891694,0.0002438861,0.3066022,0.0001221626,0.0006346379,0.004396993,0.008191195],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4149471,0.05834781,0.5212908,0.0002618277,0.0003054635,0.001920301,0.000006372933,0.002915283,0.000005069072],"genre_scores_gemma":[0.9220911,0.0007407668,0.0756472,0.0007801689,0.0001703249,0.0003960948,0.000003629399,0.0001136979,0.00005700815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.507144,"threshold_uncertainty_score":0.9998683,"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."}}