{"id":"W161357454","doi":"10.15388/infedu.2006.01","title":"Random Factors in IOI 2005 Test Case Scoring","year":2006,"lang":"en","type":"article","venue":"Informatics in Education","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Test (biology); Statistics; Olympiad; Rank (graph theory); Confidence interval; Variance (accounting); Population; Computer science; Econometrics; Mathematics; Artificial intelligence; Demography; Mathematics education","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":[0.000420592,0.00007814785,0.00008548067,0.0004579824,0.00003041028,0.0001257414,0.0002910955,0.00004255661,0.000004826799],"category_scores_gemma":[0.0007551277,0.0000788228,0.00001497199,0.0005483043,0.00001247522,0.0007973799,0.00006462036,0.0001740815,0.00002864801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002776273,"about_ca_system_score_gemma":0.0002356857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007199104,"about_ca_topic_score_gemma":0.0002471514,"domain_scores_codex":[0.9991386,0.00001253537,0.0003529161,0.00007164462,0.0001845023,0.0002398264],"domain_scores_gemma":[0.9988126,0.0007693554,0.00005246243,0.0002844981,0.00004064671,0.00004041063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002933515,0.0004319227,0.8996034,0.0001775578,0.000002694015,0.0000447722,0.01515711,0.04240064,0.00005131596,0.002905442,0.001979511,0.03724266],"study_design_scores_gemma":[0.002188669,0.0000532505,0.5717583,0.0003719822,0.000003040972,0.000468756,0.003359235,0.4108222,0.003090186,0.00291946,0.004269326,0.0006956313],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9610695,0.00004963113,0.03716609,0.00006285722,0.0005265852,0.00018139,7.308694e-7,0.00007444774,0.0008688124],"genre_scores_gemma":[0.9775066,0.000005172468,0.0222989,0.00001758888,0.00004856159,0.00003006372,0.000005040097,0.000004717459,0.00008330077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3684215,"threshold_uncertainty_score":0.32143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01197712325499854,"score_gpt":0.2779785689758177,"score_spread":0.2660014457208191,"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."}}