{"id":"W2160590935","doi":"10.1109/icsm.2009.5306383","title":"An empirical study on the risks of using off-the-shelf techniques for processing mailing list data","year":2009,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Data processing; Software; Data science; Empirical research; World Wide Web; Database; Information retrieval; Data mining","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":[0.00212007,0.0001151019,0.0001672201,0.00004241307,0.0003664212,0.0001652652,0.001945767,0.00004896718,0.000001501861],"category_scores_gemma":[0.0001076958,0.00005400748,0.0000379748,0.000312817,0.00005644135,0.0005635212,0.0001891667,0.0001223778,7.015839e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002577298,"about_ca_system_score_gemma":0.00009677704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006130131,"about_ca_topic_score_gemma":0.00001095794,"domain_scores_codex":[0.9986914,0.0001118888,0.0003240415,0.0004027129,0.0002802701,0.0001896613],"domain_scores_gemma":[0.9977497,0.0002084001,0.0001286974,0.001750328,0.0001314736,0.0000313524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008422246,0.002222539,0.1405496,0.0001220369,0.00003709876,0.000002884558,0.007852455,0.0003089788,0.001693331,0.0006997489,0.001483139,0.844944],"study_design_scores_gemma":[0.0003092458,0.00143541,0.0348271,0.0001330403,0.00003492664,0.00001171524,0.001779931,0.947275,0.01090345,0.001675637,0.001317476,0.0002970467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.53706,0.00004135713,0.4605762,0.001048833,0.0000651621,0.0008813856,0.000002910346,0.0001815228,0.0001426704],"genre_scores_gemma":[0.967931,0.000001511066,0.03146322,0.0004868096,0.00008874542,0.00001358488,0.000001593352,0.000005036151,0.000008531151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9469661,"threshold_uncertainty_score":0.3615751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2279503073911953,"score_gpt":0.4522758268410009,"score_spread":0.2243255194498057,"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."}}