{"id":"W1586702196","doi":"10.19173/irrodl.v13i3.1176","title":"Identification of conflicting questions in the PARES system","year":2012,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cheating; Test (biology); Computer science; Vocabulary; Similarity (geometry); Mathematics education; Identification (biology); Space (punctuation); Artificial intelligence; Mathematics; Psychology; Linguistics; Image (mathematics); Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01069682,0.001418134,0.001888365,0.00406278,0.0007114751,0.003681119,0.003284131,0.002193806,0.01205234],"category_scores_gemma":[0.04109887,0.0009994588,0.001215643,0.001624336,0.0009213893,0.006263628,0.005556856,0.001907799,0.006673614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049123,"about_ca_system_score_gemma":0.001381289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001447892,"about_ca_topic_score_gemma":0.001438281,"domain_scores_codex":[0.9873399,0.003234716,0.001478381,0.002597225,0.00493494,0.0004147866],"domain_scores_gemma":[0.9626341,0.02313358,0.00342231,0.005530747,0.004310115,0.0009692019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005684665,0.001420669,0.03728932,0.001257371,0.0003676268,0.002288627,0.002103504,0.01584377,0.03056646,0.01120154,0.05838923,0.8335872],"study_design_scores_gemma":[0.0005172811,0.001500156,0.02696365,0.0002368023,0.0001588788,0.00255028,0.001074483,0.8087465,0.06063551,0.02138934,0.0759611,0.0002660958],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2021571,0.0007573787,0.508588,0.001658777,0.00028063,0.002570655,0.007036958,0.2633477,0.01360275],"genre_scores_gemma":[0.5668164,0.0002722216,0.3981548,0.001273346,0.0002240423,0.001094754,0.01453496,0.002550411,0.01507902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01205234,"threshold_uncertainty_score":0.05657083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3772440652981727,"score_gpt":0.587940438919133,"score_spread":0.2106963736209603,"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."}}