{"id":"W2012086719","doi":"10.1145/1022494.1022541","title":"Empirical studies of software testing techniques","year":2004,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Empirical research; Software testing; Software reliability testing; Software engineering; Regression testing; Test strategy; Software; Software construction; System integration testing; Software performance testing; Software development; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03494538,0.0005231655,0.0004384935,0.005149693,0.0009314025,0.002310845,0.001826475,0.001157342,0.004283499],"category_scores_gemma":[0.3678264,0.0004697949,0.0003942089,0.006933367,0.002666486,0.005938637,0.001859395,0.002674097,0.0007340473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001115902,"about_ca_system_score_gemma":0.001416562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001767906,"about_ca_topic_score_gemma":0.002000688,"domain_scores_codex":[0.9454612,0.03538168,0.004239487,0.002312351,0.01168869,0.0009166244],"domain_scores_gemma":[0.2158119,0.7080641,0.03223161,0.01402037,0.02839542,0.001476615],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005303753,0.003489877,0.5723374,0.004114528,0.0006939192,0.0004026322,0.0198199,0.003852755,0.00194553,0.06700066,0.007600837,0.3182116],"study_design_scores_gemma":[0.0002330931,0.003506568,0.7939827,0.009879874,0.0005801651,0.002319269,0.03771085,0.01692139,0.008162175,0.04705163,0.07946543,0.0001868216],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8611504,0.02413422,0.0472495,0.007505211,0.0003252865,0.0005344324,0.001058603,0.0001096088,0.0579327],"genre_scores_gemma":[0.9745874,0.00833524,0.01282388,0.0009953652,0.00024154,0.0003232575,0.0007178183,0.00007340423,0.00190207],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9650546,"threshold_uncertainty_score":0.1848111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07925087812671783,"score_gpt":0.3242008907103558,"score_spread":0.244950012583638,"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."}}