{"id":"W2912962050","doi":"10.1109/beliv.2018.8634420","title":"How to Evaluate an Evaluation Study? Comparing and Contrasting Practices in Vis with Those of Other Disciplines : Position Paper","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Checklist; Position (finance); Position paper; Resource (disambiguation); Empirical research; Psychology; Qualitative research; Engineering ethics; Management science; Sociology; Applied psychology; Social science; Computer science; Epistemology; Engineering; Cognitive psychology; Business; World Wide Web","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":[0.001084811,0.00006847282,0.0001116659,0.00009363568,0.00005833755,0.000260162,0.0001543288,0.00001182677,0.00001049474],"category_scores_gemma":[0.0001623872,0.00004729886,0.000005125428,0.0002989776,0.00002489057,0.001441531,0.00009022477,0.00002387897,0.000001293339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001228194,"about_ca_system_score_gemma":0.0000295494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001382929,"about_ca_topic_score_gemma":0.002379004,"domain_scores_codex":[0.999054,0.0001626877,0.000140239,0.0002316921,0.0003246863,0.0000867443],"domain_scores_gemma":[0.9992391,0.00005321715,0.0001729562,0.0002062476,0.0002860481,0.00004240163],"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":[0.0001111866,0.001308462,0.8951656,0.00003012024,0.00008103425,0.000002390403,0.02093653,0.0009754171,0.00874747,0.01696658,0.00008287666,0.05559239],"study_design_scores_gemma":[0.0007135611,0.0005059071,0.1910212,0.0000405491,0.00002514465,0.000001188251,0.001526215,0.8054283,0.0004361825,0.0001915599,0.00002374137,0.00008644402],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7966839,0.000004047367,0.2016678,0.0008277911,0.00002303758,0.0002790387,8.0025e-7,0.00002095398,0.0004926272],"genre_scores_gemma":[0.9885027,4.18407e-7,0.01119169,0.000232711,0.00002236238,0.000008085694,0.000002773285,0.000004033671,0.00003520165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8044528,"threshold_uncertainty_score":0.2508748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1263585004118408,"score_gpt":0.4299767174871811,"score_spread":0.3036182170753403,"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."}}