{"id":"W7053140624","doi":"","title":"Understanding Test Convention Consistency as a Dimension of Test Quality","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Dimension (graph theory); Test (biology); Consistency (knowledge bases); Quality (philosophy); Convention","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02385049,0.0005897653,0.0005749317,0.007346953,0.0008029339,0.006940636,0.001207711,0.001432477,0.0015084],"category_scores_gemma":[0.2108527,0.0005329067,0.0006770926,0.005327382,0.00316695,0.01217353,0.003208889,0.002553143,0.0003250272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002167947,"about_ca_system_score_gemma":0.002704532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003684158,"about_ca_topic_score_gemma":0.003193553,"domain_scores_codex":[0.9682487,0.01092692,0.003367486,0.002809218,0.01351037,0.001137227],"domain_scores_gemma":[0.6512805,0.2555089,0.03658902,0.01871325,0.03528374,0.002624507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003726657,0.0002305878,0.4456545,0.001570385,0.0002821607,0.0004409303,0.01907347,0.01485166,0.01372123,0.08386236,0.005553613,0.4143865],"study_design_scores_gemma":[0.00009322611,0.001281932,0.6315821,0.002761347,0.0004283394,0.001798797,0.01637871,0.07277888,0.02539503,0.1972539,0.04988972,0.000358088],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6562939,0.005918956,0.2999039,0.00922033,0.0001708014,0.0002371411,0.001095079,0.001624807,0.02553519],"genre_scores_gemma":[0.9427458,0.0009040834,0.05338635,0.0005516717,0.00009690254,0.0001540616,0.0008014629,0.0002808406,0.001078837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02385049,"threshold_uncertainty_score":0.1261349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06926718033352623,"score_gpt":0.3150738044662688,"score_spread":0.2458066241327426,"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."}}