{"id":"W2005994535","doi":"10.3406/medi.2002.1536","title":"La lemmatisation et l'encodage grammatical permettent-ils de reconnaître l'auteur d'un texte ?","year":2002,"lang":"en","type":"article","venue":"Médiévales","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Linguistic Association","funders":"","keywords":"Lemmatisation; Linguistics; Authorship attribution; Computer science; Artificial intelligence; Point (geometry); Corpus linguistics; Natural language processing; Humanities; Philosophy; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0008968642,0.0001785959,0.0001815513,0.000134184,0.0001300834,0.0003510837,0.0007897622,0.0001426348,0.0001582659],"category_scores_gemma":[0.0003077917,0.0001566116,0.00008370569,0.0002896374,0.00008352178,0.000670781,0.0001897771,0.000308392,0.0001142837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007511122,"about_ca_system_score_gemma":0.00003638212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002299972,"about_ca_topic_score_gemma":0.00001130224,"domain_scores_codex":[0.9983516,0.0003579931,0.0002630501,0.0003482261,0.0002912425,0.0003878479],"domain_scores_gemma":[0.9990032,0.0002566184,0.0001091241,0.0004657949,0.00005308938,0.0001121333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000344819,0.0001224387,0.0009922902,0.00008991572,0.00002080977,0.0001610271,0.003612354,0.000004808036,0.004528222,0.1811886,0.006012278,0.8032638],"study_design_scores_gemma":[0.001657599,0.0004312916,0.01037799,0.000870148,0.000104127,0.002137308,0.0005109123,0.2622344,0.1049383,0.5480112,0.0661841,0.002542611],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08117234,0.002399253,0.9066375,0.004705053,0.0001139669,0.0002038887,0.000005681434,0.001483283,0.003279015],"genre_scores_gemma":[0.4847992,0.00006438207,0.5137309,0.0007122333,0.00003836637,0.00002130163,0.000003669541,0.00001426391,0.0006155759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8007212,"threshold_uncertainty_score":0.6386434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02342428150521207,"score_gpt":0.2706678659825323,"score_spread":0.2472435844773203,"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."}}