{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002094996,0.0004840126,0.0005289155,0.000264129,0.0005057723,0.006071339,0.003599722,0.0005555517,0.00004634488],"category_scores_gemma":[0.008341064,0.0004248177,0.0001903113,0.0006717311,0.00172601,0.01439754,0.001085247,0.0006326451,0.00001142615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003970301,"about_ca_system_score_gemma":0.0008383069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002093259,"about_ca_topic_score_gemma":0.0000422866,"domain_scores_codex":[0.99699,0.000149011,0.0007331008,0.0005737111,0.0005183937,0.001035845],"domain_scores_gemma":[0.9827532,0.0005109867,0.0009086497,0.0004293155,0.01516191,0.0002359317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006474919,0.0002790334,0.5284957,0.001411279,0.000113149,0.000001209382,0.06097,0.00008461911,0.1496331,0.05551453,0.00170048,0.2017322],"study_design_scores_gemma":[0.0005656302,0.0003104968,0.709404,0.001183106,0.000108366,0.0001000474,0.008348114,0.07164782,0.160647,0.03810056,0.009036554,0.0005483064],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9731208,0.0009290096,0.01517686,0.005419915,0.0001064803,0.0005586551,0.00003303208,0.0002081433,0.004447079],"genre_scores_gemma":[0.9641865,0.001980167,0.0317372,0.0001500483,0.00008241877,0.000219789,0.000002891802,0.00003430987,0.001606622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2011839,"threshold_uncertainty_score":0.9998204,"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."}}