{"id":"W4399906408","doi":"10.18280/ria.380307","title":"A New Algorithm for Arabic Document Clustering Utilizing Maximal Wordsets","year":2024,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Arabic; Cluster analysis; Document clustering; Computer science; Artificial intelligence; Information retrieval; Algorithm; Natural language processing; Pattern recognition (psychology); Linguistics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007192574,0.0004292501,0.0003740037,0.0003628349,0.0003238049,0.001857456,0.001339668,0.0002833975,0.0007027671],"category_scores_gemma":[0.0001264329,0.0004597354,0.0003443717,0.001294737,0.0001910451,0.001399913,0.0005463106,0.0004421081,0.001940551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002995316,"about_ca_system_score_gemma":0.0003293999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001688697,"about_ca_topic_score_gemma":0.00003160916,"domain_scores_codex":[0.996529,0.00005863659,0.0008950742,0.001236361,0.0003190777,0.0009618027],"domain_scores_gemma":[0.9979886,0.0004502852,0.0001519826,0.001032307,0.0001398165,0.0002369971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000504354,0.00004470728,0.000002774626,0.0002477863,0.00003737922,0.00003655463,0.001579029,0.001603694,0.0003439692,0.2416426,0.00795224,0.7465042],"study_design_scores_gemma":[0.00003912424,0.0001659591,0.000004199201,0.0006856364,0.00003060235,0.00007322297,0.0008792715,0.6325223,0.02062103,0.04424973,0.3003834,0.000345461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000801753,0.03991307,0.9246999,0.02435437,0.007034466,0.0007990773,0.00001937967,0.0009521493,0.002147403],"genre_scores_gemma":[0.1270357,0.002656402,0.6678107,0.0003366834,0.001343545,0.0003218667,0.00002457993,0.000110842,0.2003597],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7461587,"threshold_uncertainty_score":0.9997854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07427204738448545,"score_gpt":0.3190446043352724,"score_spread":0.2447725569507869,"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."}}