{"id":"W4411440374","doi":"10.1007/s10664-025-10661-x","title":"Supporting multi-dimensional unit test classification","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Unit testing; Test (biology); Unit (ring theory); Artificial intelligence; Pattern recognition (psychology); Geology; Psychology; Operating system; Mathematics education","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":[],"consensus_categories":[],"category_scores_codex":[0.0003653619,0.0001941907,0.0001849415,0.0002284458,0.000142968,0.0001156378,0.0005868498,0.0001152785,0.000006931518],"category_scores_gemma":[0.005936855,0.000190091,0.00007474222,0.0008629489,0.00002260435,0.0002135735,0.0002878471,0.0002866406,0.00003096503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000822188,"about_ca_system_score_gemma":0.00009998502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001242957,"about_ca_topic_score_gemma":6.606442e-7,"domain_scores_codex":[0.9986003,0.00002283219,0.0003376119,0.000430118,0.0002171773,0.0003919306],"domain_scores_gemma":[0.997534,0.001668195,0.00007039469,0.0005045161,0.0001163369,0.000106585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002352826,0.0002293597,0.9329785,0.00009577847,0.00002985875,0.00003917788,0.0001716135,0.003557849,0.0008075076,0.001336853,0.03457522,0.02617599],"study_design_scores_gemma":[0.0002728696,0.00004271021,0.3415488,0.0001941406,0.00001035179,0.00002094138,0.000001862769,0.6451411,0.001129043,0.002058849,0.009193354,0.0003860488],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01067997,0.0001137915,0.9713554,0.0006611663,0.0003043518,0.0001116766,0.000001854911,0.01671683,0.00005499219],"genre_scores_gemma":[0.4288867,9.331803e-7,0.5701858,0.0005349859,0.00003781327,0.00003010066,0.000006478042,0.00001442476,0.0003027218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6415832,"threshold_uncertainty_score":0.7751687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04423106979949689,"score_gpt":0.3406725485906861,"score_spread":0.2964414787911893,"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."}}