{"id":"W2885406936","doi":"10.48550/arxiv.1812.05168","title":"Searching for Relevant Lessons Learned Using Hybrid Information Retrieval Classifiers: A Case Study in Software Engineering","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Information retrieval; Artificial intelligence; Software engineering; Software; Machine learning; Data mining; Data science; 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":[],"consensus_categories":[],"category_scores_codex":[0.00049152,0.0001200964,0.0001324855,0.0003433276,0.0002072966,0.0001150528,0.0004187632,0.00004390721,0.000001530186],"category_scores_gemma":[0.0002557944,0.0001436317,0.00004859051,0.0005495856,0.00002744388,0.001566236,0.0002734498,0.0001869524,0.00000724411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002353579,"about_ca_system_score_gemma":0.0001133967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000317836,"about_ca_topic_score_gemma":0.00008804019,"domain_scores_codex":[0.9990042,0.00005664353,0.0001822504,0.0003613376,0.00007905698,0.0003164563],"domain_scores_gemma":[0.9991349,0.0001463509,0.00007971175,0.0004302242,0.0001224961,0.00008631717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001965337,0.0002228929,0.01475302,0.0001338572,0.00008716101,0.004215512,0.01355816,0.8870659,0.0005101996,0.06431263,0.00001777757,0.01492631],"study_design_scores_gemma":[0.0007866638,0.0001138532,0.0002035386,0.00003092143,0.00001076936,0.00009698368,0.001221611,0.9963957,0.0001291127,0.0007608616,0.00008723048,0.0001627252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5002413,0.000001438452,0.4993768,0.00001919113,0.00009214727,0.0001821969,0.000001374165,0.00007306853,0.00001246423],"genre_scores_gemma":[0.9790511,0.000001670316,0.02084547,0.00002419996,0.00004438099,4.229133e-7,0.000001077527,0.000007640368,0.00002410354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4788097,"threshold_uncertainty_score":0.5857133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1777772530138275,"score_gpt":0.2551591839102264,"score_spread":0.07738193089639889,"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."}}