{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001588185,0.0005625989,0.0005874027,0.0002367691,0.002403606,0.0009270622,0.002226565,0.0004098318,0.002008594],"category_scores_gemma":[0.0002103851,0.0004270161,0.0004578689,0.001932227,0.001003951,0.0004690565,0.0006883685,0.0007283585,0.001788736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003251977,"about_ca_system_score_gemma":0.0006418236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001343148,"about_ca_topic_score_gemma":0.001195201,"domain_scores_codex":[0.9952185,0.0005483138,0.0007914386,0.000869768,0.001178284,0.001393656],"domain_scores_gemma":[0.9975355,0.0006968841,0.0002849445,0.0009994599,0.0002531358,0.0002300826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001617323,0.0008032774,0.1049942,0.0001598471,0.0008037431,0.00002700498,0.03653573,0.00001183575,0.001039822,0.196016,0.6401635,0.0192833],"study_design_scores_gemma":[0.001316742,0.0001226612,0.07373783,0.0001918186,0.0005493648,0.000001755566,0.02115323,0.0002460551,0.000544487,0.0136767,0.8876441,0.0008152685],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.05214056,0.003770769,0.0003379576,0.06497291,0.0115393,0.001390437,0.0000307707,0.0003035079,0.8655138],"genre_scores_gemma":[0.7864155,0.0008913635,0.0001190484,0.006458654,0.001347669,0.0001005282,0.00001499319,0.00003685799,0.2046154],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.734275,"threshold_uncertainty_score":0.9998181,"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."}}