{"id":"W3131420591","doi":"10.4000/corpus.5422","title":"Le corpus comme portail pour l’étude de la variation (socio)linguistique","year":2021,"lang":"fr","type":"article","venue":"Corpus","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sociolinguistics; Vernacular; Linguistics; Annotation; Variation (astronomy); Variety (cybernetics); Computer science; Citation; Coding (social sciences); Corpus linguistics; Natural language processing; Sociology; Artificial intelligence; World Wide Web; Philosophy; Social science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001558358,0.000208876,0.0003302374,0.00005438464,0.0005903378,0.0001638571,0.000289947,0.0006204038,0.001200172],"category_scores_gemma":[0.006424254,0.0002715178,0.0001586904,0.0004031405,0.0004891059,0.00007417805,0.000106128,0.0004715406,0.0003604559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003200521,"about_ca_system_score_gemma":0.00383391,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01099208,"about_ca_topic_score_gemma":0.00255754,"domain_scores_codex":[0.9966778,0.00158732,0.0004415679,0.0004229917,0.0003023534,0.0005680386],"domain_scores_gemma":[0.9974335,0.001029195,0.0003258124,0.0003154218,0.000635381,0.0002607143],"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":[0.00001272547,0.0003836495,0.008713735,0.00002987174,0.00007303542,0.0007322965,0.01191982,0.00006797779,0.001209039,0.9660585,0.007533441,0.003265913],"study_design_scores_gemma":[0.001341808,0.00004851753,0.03445986,0.00006881914,0.000163407,0.0001906142,0.001897088,0.0008013679,0.0006216469,0.1423197,0.8176414,0.0004457136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1186391,0.01190635,0.05760043,0.09192097,0.02977787,0.0005988528,0.0001792108,0.000493539,0.6888837],"genre_scores_gemma":[0.9447779,0.00101407,0.005143934,0.004341403,0.002825298,0.00001781566,0.0000643836,0.00003686146,0.04177832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8261388,"threshold_uncertainty_score":0.9999737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03260862938634945,"score_gpt":0.3295949799492386,"score_spread":0.2969863505628891,"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."}}