{"id":"W4407319717","doi":"10.31224/4360","title":"Leveraging Order-Theoretic Tournament Graphs for Assessing Internal Consistency in Survey-Based Instruments Across Diverse Scenarios","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Tournament; Consistency (knowledge bases); Order (exchange); Internal consistency; Computer science; Econometrics; Data science; Mathematics; Information retrieval; Business; Statistics; Artificial intelligence; Combinatorics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08678196,0.001552099,0.00134418,0.006622757,0.001259815,0.003982796,0.001622955,0.001540162,0.001902088],"category_scores_gemma":[0.3257352,0.0006535383,0.001757855,0.004412191,0.002406415,0.004540949,0.003004587,0.001972272,0.0003132516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001757278,"about_ca_system_score_gemma":0.00159041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001616493,"about_ca_topic_score_gemma":0.001900882,"domain_scores_codex":[0.925528,0.05440278,0.003964563,0.006171557,0.008901368,0.001031829],"domain_scores_gemma":[0.6174127,0.3198569,0.02145004,0.02403186,0.01538844,0.001860174],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001801396,0.000871915,0.283681,0.000968746,0.002335051,0.0004151219,0.006126317,0.1720263,0.003467496,0.1346154,0.004865272,0.3888259],"study_design_scores_gemma":[0.0001889429,0.001185507,0.05101828,0.0002388714,0.0002547793,0.0002677389,0.001195859,0.7412198,0.002291772,0.1984146,0.003526161,0.0001978147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2404098,0.0003074919,0.7526846,0.000420044,0.000123298,0.0006730934,0.0004583506,0.0005253062,0.004398097],"genre_scores_gemma":[0.8510234,0.00008711847,0.1467111,0.0001569187,0.00004140419,0.0009957476,0.000584026,0.00008596345,0.000314431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.913218,"threshold_uncertainty_score":0.4589523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2453987452272297,"score_gpt":0.5055707140056989,"score_spread":0.2601719687784692,"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."}}