{"id":"W4407364769","doi":"10.36227/techrxiv.173933234.41986222/v1","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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","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; Data science; Econometrics; Mathematics; Business; Statistics; Artificial intelligence; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.07730279,0.001382121,0.001219323,0.006432273,0.001154606,0.003637054,0.001520321,0.001358902,0.00169433],"category_scores_gemma":[0.3026259,0.0006056227,0.001604939,0.003986176,0.002191736,0.004342873,0.002807189,0.001837801,0.0002755577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001670208,"about_ca_system_score_gemma":0.001555103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001651071,"about_ca_topic_score_gemma":0.001947148,"domain_scores_codex":[0.9366543,0.04527019,0.003550495,0.005406549,0.008188987,0.0009295374],"domain_scores_gemma":[0.6454983,0.2961253,0.01964886,0.02179967,0.01510308,0.001824768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001784856,0.0008389947,0.2923697,0.0009328091,0.002080478,0.000405882,0.006255102,0.1673346,0.003830573,0.1202681,0.00421214,0.3996868],"study_design_scores_gemma":[0.0001862004,0.001294026,0.0548807,0.0002291912,0.0002537892,0.0002886156,0.001240332,0.7525221,0.002601942,0.1830157,0.003292806,0.000194507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2584259,0.000271084,0.7352723,0.0003454885,0.0001020014,0.0006151525,0.0004099957,0.0004908441,0.004067165],"genre_scores_gemma":[0.858065,0.00007845854,0.1399679,0.0001267969,0.00003319898,0.0008579429,0.0005074432,0.00007312917,0.0002901086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07730279,"threshold_uncertainty_score":0.4088211,"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."}}