{"id":"W2082055394","doi":"10.1007/s10791-012-9218-8","title":"Increasing evaluation sensitivity to diversity","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Diversity (politics); Context (archaeology); Information retrieval; Discriminative model; Measure (data warehouse); Data science; Data mining; Artificial intelligence; Geography","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":[0.002391295,0.0001236089,0.0001194852,0.0003300906,0.0004872083,0.0005975086,0.0003785559,0.00007857154,0.0002231839],"category_scores_gemma":[0.0008201572,0.0001161017,0.00005822012,0.0009015072,0.00002400565,0.0097673,0.0007756918,0.0001466503,0.004764339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002195849,"about_ca_system_score_gemma":0.0001279681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003487538,"about_ca_topic_score_gemma":0.00000251352,"domain_scores_codex":[0.9977418,0.0001789902,0.0003674117,0.0001246939,0.001288962,0.0002981759],"domain_scores_gemma":[0.9978443,0.0001146669,0.0001337514,0.0003573127,0.001313458,0.0002364445],"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":[0.0001720586,0.00009907965,0.01463191,0.00006030949,0.00003855972,0.000004711017,0.01948855,0.00214186,0.003466099,0.02143931,0.01012359,0.9283339],"study_design_scores_gemma":[0.00119771,0.0002337372,0.4264012,0.00002746946,0.00001751103,0.00008361277,0.0004474405,0.5546914,0.006403589,0.001120199,0.008793486,0.0005826814],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7435578,0.000001817908,0.2481371,0.001135417,0.0003213805,0.000871696,0.000006047756,0.0002102472,0.005758462],"genre_scores_gemma":[0.9894375,7.895794e-7,0.00860889,0.001836435,0.00003154971,0.00001103634,0.00002732648,0.000002289664,0.00004420911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9277513,"threshold_uncertainty_score":0.9960105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02380544427014461,"score_gpt":0.2593833951838307,"score_spread":0.2355779509136861,"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."}}