{"id":"W2044863546","doi":"10.1007/s10009-013-0277-y","title":"Generating effective tests for concurrent programs via AI automated planning techniques","year":2013,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Concurrency; Atomicity; Correctness; Interleaving; Programming language; Debugging; Set (abstract data type); Theory of computation","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":[0.001588628,0.0015723,0.0008135557,0.002077835,0.0008632274,0.001362707,0.002050118,0.00103801,0.004909793],"category_scores_gemma":[0.01619775,0.0008104877,0.001314281,0.001358921,0.001934916,0.001908624,0.001676763,0.001524065,0.0005015473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001170797,"about_ca_system_score_gemma":0.002618457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005867213,"about_ca_topic_score_gemma":0.01164608,"domain_scores_codex":[0.9972659,0.000769824,0.0001563363,0.0003600743,0.001169919,0.0002778724],"domain_scores_gemma":[0.9805736,0.01620078,0.0007819539,0.001017203,0.001212718,0.000213801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007209243,0.0005395392,0.004780043,0.001006457,0.0001643047,0.00144515,0.0006772916,0.5215262,0.04241754,0.05518133,0.003915852,0.3676254],"study_design_scores_gemma":[0.0001625085,0.0002503221,0.000513494,0.00005326083,0.000107944,0.000150096,0.0001570158,0.9175482,0.02937567,0.04979651,0.0018516,0.00003352203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04547626,0.0001389623,0.9447534,0.0001957981,0.0000391885,0.0002661237,0.0002083229,0.00508102,0.003840994],"genre_scores_gemma":[0.4460058,0.0001036992,0.5518357,0.00009564134,0.00002463193,0.0002806055,0.0003489277,0.0004490627,0.0008559314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005867213,"threshold_uncertainty_score":0.01642483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02929224509674527,"score_gpt":0.335350900474194,"score_spread":0.3060586553774487,"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."}}