{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004689904,0.0003455321,0.0003518491,0.0006806186,0.0003316097,0.0008320075,0.001626323,0.0003453835,0.00000525516],"category_scores_gemma":[0.001231316,0.0002997217,0.0002459336,0.0003073681,0.0001215674,0.0009502738,0.00009385577,0.0005918337,0.00001087733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002187116,"about_ca_system_score_gemma":0.00008577346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007121532,"about_ca_topic_score_gemma":9.595544e-7,"domain_scores_codex":[0.9978967,0.00004757668,0.0005894704,0.000528432,0.0004129331,0.0005248273],"domain_scores_gemma":[0.9970033,0.0009718363,0.0001533913,0.0003175418,0.001445592,0.000108407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002585372,0.0001861763,0.001561344,0.00001988464,0.0001532117,0.00002445925,0.0001061942,0.00009755297,0.002213247,0.003812407,0.006533229,0.9852664],"study_design_scores_gemma":[0.005981523,0.01089397,0.002031214,0.003239589,0.0001322941,0.003632688,0.00003389769,0.3577022,0.186334,0.3913365,0.03597181,0.002710374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01882311,0.0001029873,0.9490025,0.002855446,0.0009711447,0.00178665,0.00001868436,0.02643009,0.000009404893],"genre_scores_gemma":[0.4489124,0.000005175812,0.5473067,0.001092264,0.0002158489,0.002383321,0.00002676391,0.0000421462,0.0000154953],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.982556,"threshold_uncertainty_score":0.9999455,"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."}}