{"id":"W4416328737","doi":"10.7592/tertium.2025.10.1.322","title":"Beyond the Bubble","year":2025,"lang":"pl","type":"article","venue":"Półrocznik Językoznawczy Tertium","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Summative assessment; Construct (python library); Excellence; Test (biology); Foreign language; Language assessment; Government (linguistics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002059859,0.0007580142,0.0006742503,0.001758775,0.008434788,0.01334438,0.001361523,0.004232443,0.1230205],"category_scores_gemma":[0.01305459,0.000354591,0.000429223,0.001993016,0.009259124,0.01957634,0.008457419,0.005638978,0.03607234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006150187,"about_ca_system_score_gemma":0.00389756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01603334,"about_ca_topic_score_gemma":0.01347383,"domain_scores_codex":[0.9976587,0.0007147733,0.00007125267,0.0005337467,0.0005141958,0.000507306],"domain_scores_gemma":[0.9973328,0.0008219403,0.0001858769,0.0006582314,0.0005732038,0.0004280845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003794715,0.00001066683,0.000397853,0.00008784606,0.000007157247,0.0001834043,0.005005812,0.00006867868,0.0001426597,0.6688455,0.2655834,0.05962908],"study_design_scores_gemma":[0.000001982421,0.000003710077,0.0001086214,0.00007296851,0.000001308667,0.00005504848,0.0009266821,0.00002790605,0.00002563989,0.01925074,0.9795213,0.000004021463],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005108268,0.02015615,0.005040151,0.1145069,0.01134605,0.00005676228,0.0006698685,0.0005584749,0.8425574],"genre_scores_gemma":[0.1924171,0.01368166,0.003496751,0.03683417,0.006226761,0.0001400614,0.0008839901,0.001506013,0.7448134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1230205,"threshold_uncertainty_score":0.4115446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01482895853523709,"score_gpt":0.3296920592079808,"score_spread":0.3148631006727437,"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."}}