{"id":"W2971324562","doi":"10.1007/978-3-030-28374-2_4","title":"Frequent Itemsets as Descriptors of Textual Records","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Medoid; Similarity (geometry); Data mining; Set (abstract data type); Hierarchical clustering; Process (computing); Association rule learning; Cluster analysis; Artificial intelligence; Information retrieval; Data set; Pattern recognition (psychology); Natural language processing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005999703,0.0003951971,0.0004925161,0.0006187275,0.0001390031,0.0003091099,0.004099029,0.0002168286,0.00004340525],"category_scores_gemma":[0.00009570565,0.0003630413,0.0001082794,0.0007117238,0.0005305345,0.0006399387,0.001351314,0.000541523,0.0001772245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868927,"about_ca_system_score_gemma":0.000915606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001774003,"about_ca_topic_score_gemma":0.00003946762,"domain_scores_codex":[0.9967825,0.00001669578,0.0005574377,0.001320428,0.0008522209,0.0004706485],"domain_scores_gemma":[0.996971,0.0003232949,0.0003581845,0.001907857,0.0002899799,0.0001497489],"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":[0.000001195615,0.00003301277,0.00006846977,0.00002731734,0.00001044071,0.0000146002,0.0003607755,0.001282073,0.0001653434,0.0891438,0.0001672439,0.9087257],"study_design_scores_gemma":[0.0009547404,0.001346019,0.00142134,0.002107929,0.00004455656,0.0003504315,0.000002197464,0.6718776,0.01129023,0.240902,0.0666158,0.003087113],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003467869,0.0001907115,0.9892045,0.0004230952,0.001622735,0.0003250026,0.00003699413,0.00009732631,0.00775291],"genre_scores_gemma":[0.04797577,0.0001013821,0.9489928,0.001068845,0.000386968,0.00001720566,0.00003506539,0.000048432,0.001373458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9056386,"threshold_uncertainty_score":0.9998822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01979408017618044,"score_gpt":0.2542030724421918,"score_spread":0.2344089922660114,"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."}}