{"id":"W1532805649","doi":"10.1002/spe.2134","title":"Validating pragmatic reuse tasks by leveraging existing test suites","year":2012,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Reuse; Computer science; Correctness; Software engineering; Test suite; Test (biology); Code (set theory); Task (project management); Code reuse; Software; Test case; Programming language; Systems engineering; Machine learning; Engineering","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"],"consensus_categories":[],"category_scores_codex":[0.001302718,0.0002231332,0.0001837562,0.00009720374,0.0004216822,0.0005671369,0.001031385,0.00007172496,0.00002269665],"category_scores_gemma":[0.1289818,0.0002214102,0.00003012968,0.0005575272,0.0000890768,0.005181106,0.0009606754,0.0003806257,0.00005516671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008132691,"about_ca_system_score_gemma":0.00005716055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001189598,"about_ca_topic_score_gemma":3.482387e-7,"domain_scores_codex":[0.9977288,0.0001251485,0.000297641,0.0004796001,0.0005683613,0.0008004572],"domain_scores_gemma":[0.978325,0.02005378,0.0001737898,0.000963941,0.0001580381,0.000325466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001392418,0.0005348842,0.7109528,0.0003244281,0.00005341493,0.00009061713,0.1668601,0.00004124919,0.01723701,0.00170425,0.008352646,0.09383466],"study_design_scores_gemma":[0.004511134,0.001431583,0.1094973,0.002481428,0.0002167883,0.006562872,0.06270345,0.02347723,0.1154151,0.002217089,0.6618746,0.009611441],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4809008,0.004379393,0.5109619,0.001346543,0.0005595698,0.000320212,0.000006736104,0.001201119,0.0003237501],"genre_scores_gemma":[0.7436135,0.00005793482,0.2556456,0.0003558517,0.0001035719,0.00007265821,0.000003572728,0.00002264739,0.0001246829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.653522,"threshold_uncertainty_score":0.9028846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03397489464538216,"score_gpt":0.3258845244122648,"score_spread":0.2919096297668827,"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."}}