{"id":"W2029009258","doi":"10.1145/2348283.2348300","title":"Time-based calibration of effectiveness measures","year":2012,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Computer science; Measure (data warehouse); Process (computing); Quality (philosophy); Information retrieval; Calibration; Adaptation (eye); Data mining; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004747493,0.00003506408,0.00005429322,0.00005054008,0.00002798243,0.00001902843,0.0001519672,0.0000213257,0.00004667279],"category_scores_gemma":[0.00001985476,0.00002560709,0.00002620513,0.0001691564,0.00001862306,0.0007311135,0.00002582581,0.00002506155,0.00005368457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001153136,"about_ca_system_score_gemma":0.00003528405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008419541,"about_ca_topic_score_gemma":1.477508e-7,"domain_scores_codex":[0.9994867,0.00006701383,0.00009006824,0.00003927786,0.0002129666,0.0001039688],"domain_scores_gemma":[0.999658,0.00006652468,0.0000271408,0.0001261104,0.00007564215,0.00004658508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001669239,0.001099699,0.08855211,0.0004099206,0.00004448976,0.000001785875,0.003284631,0.001948983,0.2438714,0.41571,0.001482588,0.2434274],"study_design_scores_gemma":[0.0003311743,0.00007854793,0.04391997,0.00001263121,0.000002913921,0.00000112026,0.000006330514,0.1466636,0.8080652,0.00008508265,0.0007358653,0.00009753241],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1014823,0.00001095554,0.8959702,0.00004758797,0.00007598128,0.0001019024,7.308074e-7,0.00005838146,0.002251951],"genre_scores_gemma":[0.9954974,1.786473e-7,0.004324322,0.00006324035,0.00001029655,0.000004451576,0.000002386803,0.000001202822,0.00009653969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8940151,"threshold_uncertainty_score":0.1044227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02563785066914584,"score_gpt":0.2660673763852607,"score_spread":0.2404295257161148,"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."}}