{"id":"W2617799745","doi":"10.29173/cais355","title":"Les méthodes de classification non supervisées appliquées aux textes : mesure de la performance des résultats de clustering de documents","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Humanities; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.009541055,0.001891813,0.00216576,0.006357004,0.001384855,0.003452017,0.001830849,0.0024576,0.001277637],"category_scores_gemma":[0.03079162,0.0006267847,0.001674322,0.00371703,0.00106547,0.001743637,0.0009379145,0.00146139,0.001572083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001392309,"about_ca_system_score_gemma":0.001408408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007966727,"about_ca_topic_score_gemma":0.009925537,"domain_scores_codex":[0.9878841,0.003704664,0.001008125,0.002257859,0.004711383,0.0004338711],"domain_scores_gemma":[0.9628062,0.02039463,0.002824377,0.003282157,0.0102346,0.0004580164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002312029,0.0003959831,0.02267909,0.0009792929,0.0008570626,0.0001269851,0.0008254381,0.03011246,0.0492751,0.0009654864,0.002392925,0.8890781],"study_design_scores_gemma":[0.0003847323,0.00247171,0.09317639,0.0002803446,0.0008316802,0.001172977,0.0008216589,0.6621432,0.2229458,0.003874229,0.01150387,0.0003933221],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3674084,0.004795213,0.6161126,0.0003999274,0.0003691722,0.0007228909,0.001463998,0.005602147,0.003125488],"genre_scores_gemma":[0.5082659,0.0009682146,0.481932,0.00008912044,0.0001574084,0.0007419238,0.002004915,0.0005397199,0.005300867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009541055,"threshold_uncertainty_score":0.05045849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05746759106833514,"score_gpt":0.3074854097717187,"score_spread":0.2500178187033836,"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."}}