{"id":"W3195694877","doi":"10.1145/3447548.3470802","title":"Mixed Method Development of Evaluation Metrics","year":2021,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; Metric (unit); Context (archaeology); Data science; Selection (genetic algorithm); Artificial intelligence","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":[0.001571268,0.00004444305,0.000100788,0.00008966895,0.00002814175,0.0000326705,0.000168467,0.00002763381,0.0000387685],"category_scores_gemma":[0.00006650968,0.00003701748,0.00002779964,0.0005508953,0.000002104829,0.0001157068,0.0001441572,0.0000256285,0.000004540737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003619309,"about_ca_system_score_gemma":0.0002119327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034418,"about_ca_topic_score_gemma":0.00001382016,"domain_scores_codex":[0.9990841,0.0001507,0.0002259345,0.0001570647,0.0003103608,0.00007185365],"domain_scores_gemma":[0.9992579,0.0000735543,0.00006502709,0.0002723161,0.0003076083,0.00002356767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[1.37419e-7,0.00003272264,0.0001197145,0.00001119763,0.00001623607,0.000001125065,0.0003374631,0.000002608731,0.00231809,0.0765145,0.001437424,0.9192088],"study_design_scores_gemma":[0.0001251953,0.00001006882,0.002043308,0.00001104953,0.000004226692,0.00001105364,0.00006019827,0.04881463,0.9211752,0.005648286,0.02200985,0.00008687867],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008228142,0.0001353922,0.9809907,0.0001948198,0.0002151796,0.00007271106,9.499501e-8,0.00006601716,0.01750225],"genre_scores_gemma":[0.1388409,0.000002322359,0.8608444,0.00004603359,0.000005650174,0.00001318675,0.000001224635,0.000001706556,0.0002444857],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9191219,"threshold_uncertainty_score":0.1509529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1300077186787937,"score_gpt":0.3621521690396146,"score_spread":0.232144450360821,"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."}}