{"id":"W4407179463","doi":"10.1017/s0272263125000075","title":"The impact of collocational proficiency features on expert ratings of L2 English learners’ writing","year":2025,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Linguistics; Psychology; Language proficiency; Language assessment; Mathematics education; Philosophy","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":[0.003673872,0.0002956852,0.0002577549,0.0005607426,0.0002214734,0.001238506,0.0001676189,0.0003699517,0.002582525],"category_scores_gemma":[0.03427739,0.0001468347,0.0001494685,0.0002313921,0.0005258908,0.000460296,0.0007684298,0.0005193492,0.0003464023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002004166,"about_ca_system_score_gemma":0.0001148654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004623243,"about_ca_topic_score_gemma":0.0008677723,"domain_scores_codex":[0.9967174,0.001661059,0.0003013188,0.0004308406,0.0007833921,0.0001060248],"domain_scores_gemma":[0.931968,0.04816111,0.009677301,0.002882926,0.005246676,0.002063988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003493503,0.0008264863,0.7415956,0.0002735954,0.0002452425,0.0006462804,0.01710596,0.0006404856,0.1753876,0.0002271627,0.0004891728,0.05906888],"study_design_scores_gemma":[0.00002919883,0.001881097,0.9755721,0.00003383527,0.00004124757,0.000328624,0.003061762,0.001083414,0.01726422,0.0001350949,0.0005415475,0.00002778384],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988822,0.00003417604,0.0002008846,0.00001148579,0.000002760546,0.000005965709,0.00001714989,0.00000612246,0.0008392796],"genre_scores_gemma":[0.9991714,0.00002118787,0.0003344458,0.000008888265,0.000003928573,0.000007495113,0.0000191236,0.00000435313,0.0004292231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003673872,"threshold_uncertainty_score":0.0194295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01855927005041019,"score_gpt":0.402168913415247,"score_spread":0.3836096433648368,"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."}}