{"id":"W3035362865","doi":"10.1142/s2196888820500207","title":"New Descriptors of Textual Records: Getting Help from Frequent Itemsets","year":2020,"lang":"en","type":"article","venue":"Vietnam Journal of Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Medoid; Keyword extraction; Information retrieval; Set (abstract data type); Similarity (geometry); Process (computing); Raw data; Document clustering; Association rule learning; Artificial intelligence","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":[0.0006670695,0.0001465581,0.0003050944,0.0001712537,0.0002151101,0.0004893839,0.003551348,0.00003366238,0.0000153255],"category_scores_gemma":[0.0001255809,0.0001243455,0.00009961585,0.001520206,0.0001887951,0.001630386,0.0006542836,0.0002337208,0.00001862314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000452886,"about_ca_system_score_gemma":0.0007859941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005501295,"about_ca_topic_score_gemma":0.000001206058,"domain_scores_codex":[0.9977658,0.00003602082,0.000703766,0.0003976409,0.000811817,0.0002849439],"domain_scores_gemma":[0.9978356,0.000107078,0.0006834473,0.0004569312,0.0004365644,0.0004804107],"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":[0.000003676938,0.00006042763,0.001298806,0.000008367398,0.00002355294,0.00002376087,0.003001465,0.0006268822,0.0125432,0.003189789,0.01106468,0.9681554],"study_design_scores_gemma":[0.001479215,0.001552072,0.01896888,0.0005448011,0.00004410679,0.0002837917,0.0003079671,0.9077085,0.03460632,0.003289973,0.03040944,0.0008049207],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.047485,0.000205821,0.9480138,0.003375185,0.000746034,0.00006451934,0.000008900515,0.00003338372,0.00006736842],"genre_scores_gemma":[0.2159805,0.00001707561,0.7827387,0.0007001276,0.0005522674,4.605095e-7,8.893679e-7,0.000005782704,0.000004171397],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9673505,"threshold_uncertainty_score":0.6599347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0265998240732124,"score_gpt":0.2530871985306625,"score_spread":0.2264873744574501,"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."}}