{"id":"W4378676759","doi":"10.1109/icstw58534.2023.00071","title":"On factors that impact the relationship between code coverage and test suite effectiveness: a survey","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test suite; Test (biology); Suite; Computer science; Code coverage; Empirical research; Code (set theory); Variety (cybernetics); Test case; Programming language; Statistics; Machine learning; Artificial intelligence; Software; Mathematics; Geography","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00177098,0.0001349712,0.0001373687,0.0001186487,0.0002554654,0.0002279356,0.0003987592,0.00005665236,0.000001847948],"category_scores_gemma":[0.008675424,0.00007738162,0.0000424486,0.0006720952,0.00004493396,0.0001755747,0.000179222,0.0001668728,0.00002908878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003883678,"about_ca_system_score_gemma":0.00003326527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009471004,"about_ca_topic_score_gemma":0.00003724431,"domain_scores_codex":[0.9988662,0.0003470713,0.00009613506,0.0002757153,0.0002034192,0.0002114758],"domain_scores_gemma":[0.9198281,0.07959407,0.00004633336,0.0004407939,0.00002991312,0.00006078367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001596734,0.000006442445,0.9957241,0.000004728557,0.00000512696,0.000001726158,0.0001152444,0.0000103272,0.000002040331,0.0008303634,0.002650262,0.0006480794],"study_design_scores_gemma":[0.00008315607,0.000129394,0.9541374,0.00003493533,0.000002557127,0.000001863201,0.000001099461,0.001014948,0.0001113132,0.04437214,0.000006914215,0.000104223],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9265712,0.000009011517,0.06633101,0.0001151556,0.00004778959,0.0001801936,0.00003421262,0.006583561,0.0001278741],"genre_scores_gemma":[0.9994055,0.000001856504,0.0004083214,0.00005107144,0.000009977345,0.00001111124,0.00001811516,0.00001067497,0.00008334752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07924699,"threshold_uncertainty_score":0.9996749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1364487709068501,"score_gpt":0.3540636732012603,"score_spread":0.2176149022944102,"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."}}