{"id":"W4404883323","doi":"10.47810/clib.24.20","title":"Lexical Richness of French and Quebec Journalistic Texts","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Natural language processing; History; Artificial intelligence; Philosophy","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":[0.001394126,0.0003505484,0.0004815386,0.01920651,0.002482279,0.003288724,0.0003448187,0.0004685286,0.003789415],"category_scores_gemma":[0.01115278,0.0001474856,0.0002684721,0.009648682,0.001632677,0.001267761,0.001047953,0.0002890944,0.0002236864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004695305,"about_ca_system_score_gemma":0.001075761,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2066561,"about_ca_topic_score_gemma":0.2451914,"domain_scores_codex":[0.9978789,0.0007511186,0.0001701984,0.0003471275,0.0006449684,0.0002076345],"domain_scores_gemma":[0.989599,0.006269993,0.001521854,0.0001936812,0.001973446,0.000442153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001715587,0.0001912904,0.6040469,0.001315665,0.0004837059,0.002664492,0.2359454,0.0009501745,0.03517178,0.005494931,0.004949069,0.107071],"study_design_scores_gemma":[0.00001403658,0.00009117744,0.9459543,0.00007568448,0.00004600997,0.0009241328,0.03709878,0.0005785731,0.001112711,0.0002078422,0.01385213,0.00004466606],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923921,0.0007215403,0.0001564723,0.0001819173,0.000006554604,0.00001373179,0.001321136,0.00001890317,0.005187674],"genre_scores_gemma":[0.9974208,0.0002230441,0.0002333372,0.00003192048,0.00001987811,0.00002316666,0.0009990357,0.00001117731,0.001037611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7933439,"threshold_uncertainty_score":0.4109064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009868015370580152,"score_gpt":0.2793488759580476,"score_spread":0.2694808605874675,"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."}}