{"id":"W4412954988","doi":"10.1075/ap.21010.oco","title":"Ontological realism as a validity criterion in second-language strategic competence assessment","year":2025,"lang":"en","type":"article","venue":"Applied Pragmatics","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Atlantic School of Theology","funders":"","keywords":"Criterion validity; Realism; Psychology; Competence (human resources); Linguistics; Natural language processing; Computer science; Epistemology; Social psychology; Construct validity; Philosophy; Psychometrics; Developmental psychology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004701377,0.0002069294,0.0003241914,0.0001259037,0.0002201923,0.000409212,0.0004859484,0.00008984912,0.002693044],"category_scores_gemma":[0.00002323692,0.0001753598,0.00005248717,0.00009685312,0.0002853173,0.0001512642,0.0001547068,0.0003943639,0.00007080057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009017588,"about_ca_system_score_gemma":0.0001817479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004237896,"about_ca_topic_score_gemma":0.00592355,"domain_scores_codex":[0.9985986,0.0001805762,0.0004801015,0.0002479967,0.0002217852,0.0002709874],"domain_scores_gemma":[0.998748,0.0003476094,0.0001570677,0.0006427313,0.00005945587,0.00004510652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001137972,0.000165699,0.00005672306,0.00009538943,0.00001992996,0.00001453777,0.02093082,0.00000982074,0.0003912671,0.9772506,0.0005836047,0.0004702714],"study_design_scores_gemma":[0.001702254,0.0001500043,0.004866063,0.0002580411,0.00009674518,0.00001111226,0.3854097,0.001370471,0.0004592861,0.5766447,0.02823697,0.0007947319],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3771239,0.0001142817,0.0001544845,0.0004941064,0.0001253946,0.0003097449,0.00002237553,0.0001012394,0.6215545],"genre_scores_gemma":[0.9945415,0.00003026734,0.002113899,0.0008752742,0.00006494543,0.0001096776,0.00009975526,0.00001221934,0.002152458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6194021,"threshold_uncertainty_score":0.9982187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06455669946351476,"score_gpt":0.3518197438052697,"score_spread":0.2872630443417549,"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."}}