{"id":"W7077974436","doi":"","title":"QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Normative; Linguistic description; Linguistic analysis; Binary number; Language model; Corpus linguistics; Deep linguistic processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001379201,0.001195023,0.0003739984,0.0028483,0.002272583,0.001316679,0.001245704,0.001204475,0.012219],"category_scores_gemma":[0.008877277,0.0002349718,0.000433726,0.002338485,0.0009804583,0.001001987,0.001141244,0.001555158,0.004423701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005861136,"about_ca_system_score_gemma":0.004822869,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.6410362,"about_ca_topic_score_gemma":0.7658334,"domain_scores_codex":[0.9981717,0.0005690228,0.0001032965,0.0003866542,0.0006282814,0.0001410854],"domain_scores_gemma":[0.9945011,0.001623115,0.0002053946,0.0006196694,0.002809354,0.0002412908],"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":[0.0006005815,0.000403851,0.02993237,0.001503412,0.0001517413,0.001106181,0.005666649,0.005635644,0.01472053,0.008027465,0.7466889,0.1855627],"study_design_scores_gemma":[0.0001911667,0.000140461,0.1711833,0.0005373308,0.00007556423,0.0008655624,0.006777185,0.032543,0.01176555,0.00437413,0.7712196,0.0003271204],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.3599614,0.002988987,0.02462515,0.003623046,0.0006896324,0.000846206,0.5132664,0.01256924,0.08142997],"genre_scores_gemma":[0.4666383,0.000591627,0.02924819,0.0007640533,0.0001186132,0.0006563989,0.4818657,0.001198914,0.01891835],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6410362,"threshold_uncertainty_score":0.7221557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02136047595851664,"score_gpt":0.2567598069577669,"score_spread":0.2353993309992503,"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."}}