{"id":"W2963079908","doi":"10.1007/s10664-019-09743-4","title":"CAPS: a supervised technique for classifying Stack Overflow posts concerning API issues","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan; Queen's University","funders":"","keywords":"Computer science; Documentation; Application programming interface; Task (project management); Conditional random field; Readability; Field (mathematics); Baseline (sea); Data science; World Wide Web; Artificial intelligence; Machine learning; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005976367,0.0004188838,0.0004852533,0.000315017,0.0001105144,0.0002804288,0.001280911,0.0002596469,0.00006148635],"category_scores_gemma":[0.002801272,0.0004321014,0.0002094059,0.0007894119,0.00002594331,0.0006708861,0.0004882017,0.0005945592,0.0001376459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003459407,"about_ca_system_score_gemma":0.0001388784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248177,"about_ca_topic_score_gemma":7.002444e-7,"domain_scores_codex":[0.9970148,0.00003487282,0.0004216674,0.0008460687,0.000648731,0.001033812],"domain_scores_gemma":[0.9960266,0.002465205,0.00005913205,0.000941644,0.0001967448,0.0003106311],"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":[0.00007968644,0.000239183,0.777256,0.002357506,0.0003340075,0.0001622964,0.003168886,0.1220952,0.07263812,0.001339007,0.01137268,0.008957505],"study_design_scores_gemma":[0.004395781,0.001386503,0.1556188,0.001564178,0.00004318863,0.0001930034,0.00008394157,0.5870023,0.09297669,0.0005418306,0.1518503,0.004343489],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1388863,0.0005875709,0.856402,0.0003057814,0.0006821617,0.0009951048,0.00001196968,0.002112942,0.00001621742],"genre_scores_gemma":[0.6372389,0.00001534737,0.3613065,0.0001766145,0.0002927608,0.0004131576,0.00001827445,0.0001301486,0.0004083585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6216372,"threshold_uncertainty_score":0.9998131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0362815258937799,"score_gpt":0.3089535097084091,"score_spread":0.2726719838146292,"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."}}