{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02357434,0.001829774,0.001105611,0.003319969,0.0006724891,0.002571941,0.003537827,0.00188561,0.001668352],"category_scores_gemma":[0.1455903,0.000914175,0.001499511,0.001156719,0.002087854,0.002769984,0.002876586,0.001922436,0.0009079251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001283467,"about_ca_system_score_gemma":0.002924526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002163983,"about_ca_topic_score_gemma":0.002767916,"domain_scores_codex":[0.9540493,0.02203076,0.004790005,0.004188321,0.01346024,0.00148143],"domain_scores_gemma":[0.7427518,0.1621874,0.01751718,0.05497807,0.02083394,0.001731681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009007201,0.003527809,0.05912652,0.001583437,0.0006798279,0.002273323,0.003798576,0.1342492,0.1726423,0.01114183,0.003777787,0.6062986],"study_design_scores_gemma":[0.0005920113,0.002815837,0.02421679,0.0006862694,0.0003727498,0.001900624,0.0009675661,0.7330743,0.2033498,0.01706625,0.0146074,0.0003503213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4409041,0.0003041722,0.5428901,0.0004120602,0.00008909438,0.0007962607,0.0002864443,0.01097301,0.003344741],"genre_scores_gemma":[0.6044074,0.0001637924,0.3922604,0.0001692467,0.00002842753,0.0003715765,0.001073312,0.0008518458,0.0006740442],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02357434,"threshold_uncertainty_score":0.1246745,"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."}}