{"id":"W3163597827","doi":"10.1109/icse43902.2021.00019","title":"Studying Test Annotation Maintenance in the Wild","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Annotation; Computer science; Java; Fixture; Test (biology); Empirical research; Test case; Software engineering; Artificial intelligence; Machine learning; Programming language; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003892884,0.00004680663,0.00004899227,0.00003041781,0.000057115,0.0001259001,0.0003894151,0.00001526542,0.000001859154],"category_scores_gemma":[0.0009337039,0.00003121256,0.00001486181,0.0004936556,0.00001148547,0.000145185,0.00008791951,0.00008045552,0.000008869969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001413397,"about_ca_system_score_gemma":0.00003283736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005469281,"about_ca_topic_score_gemma":0.00002691464,"domain_scores_codex":[0.9994369,0.00004979835,0.00009476171,0.0001687457,0.0001302515,0.000119523],"domain_scores_gemma":[0.9988831,0.0006733866,0.00002261537,0.0003507748,0.00005912449,0.00001104924],"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":[0.000001673098,0.0005233741,0.3481851,0.00002479237,0.000006432198,0.0005825881,0.008452396,0.00009514827,0.0006180392,0.1063187,0.1699783,0.3652135],"study_design_scores_gemma":[0.0006768928,0.0002263508,0.391855,0.0003043782,0.000005887326,0.0004692094,0.0005563044,0.1978102,0.004026967,0.3956896,0.007758942,0.0006202835],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01367434,0.00007732683,0.9691046,0.005820524,0.00008904737,0.0000916103,2.478374e-7,0.003559095,0.007583183],"genre_scores_gemma":[0.8192859,0.000003230371,0.1785625,0.001952922,0.00001354748,0.00001200021,4.446711e-7,0.00000202765,0.0001675297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8056115,"threshold_uncertainty_score":0.1272811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03117131848671664,"score_gpt":0.2705429677314099,"score_spread":0.2393716492446933,"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."}}