{"id":"W2795368212","doi":"10.1109/saner.2018.8330213","title":"Classifying stack overflow posts on API issues","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Queen's University","funders":"","keywords":"Computer science; Documentation; Task (project management); Conditional random field; Generalizability theory; Field (mathematics); World Wide Web; Application programming interface; Baseline (sea); Data science; Software engineering; Artificial intelligence; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002041079,0.00009307248,0.0000802562,0.0001140014,0.00007482773,0.0001821129,0.0007322322,0.00004293791,0.0001584664],"category_scores_gemma":[0.0003333541,0.00007837271,0.00002676933,0.0003189473,0.00003946363,0.0002565634,0.0002513909,0.0001237439,0.001824139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005409506,"about_ca_system_score_gemma":0.00003453483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003420867,"about_ca_topic_score_gemma":0.000004942233,"domain_scores_codex":[0.998867,0.00001809992,0.0000897116,0.0002983276,0.0004047695,0.0003220515],"domain_scores_gemma":[0.9988596,0.0003021425,0.00001231243,0.0006351681,0.00009303322,0.00009778061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00005761131,0.0003990541,0.05844191,0.0001119709,0.0001230294,0.0001998504,0.003978005,0.0004488598,0.01701882,0.2660073,0.3841837,0.2690299],"study_design_scores_gemma":[0.001332798,0.002620914,0.2707351,0.0002201556,0.000004639965,0.00004667525,0.00006463298,0.2349511,0.226688,0.004789012,0.2571338,0.001413065],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2937524,0.0001334272,0.6761672,0.004060347,0.001525197,0.0002362391,0.000001416546,0.002128572,0.02199526],"genre_scores_gemma":[0.9498902,0.00000608825,0.04436377,0.0003774523,0.0002873552,0.000004721158,4.266764e-7,0.00001267378,0.005057293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6561378,"threshold_uncertainty_score":0.998953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03463733268093194,"score_gpt":0.3190475714169406,"score_spread":0.2844102387360087,"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."}}