{"id":"W4286239843","doi":"10.5281/zenodo.6866942","title":"Datasets for Data-Centric Classification and Clustering","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Data science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.003902839,0.003647375,0.002023913,0.005892353,0.001970833,0.002970799,0.005452669,0.003319693,0.02200195],"category_scores_gemma":[0.01437379,0.0006977321,0.003598036,0.007549184,0.0009640635,0.002135722,0.003829618,0.00387305,0.04400599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002467215,"about_ca_system_score_gemma":0.003268565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01081093,"about_ca_topic_score_gemma":0.01703433,"domain_scores_codex":[0.9944171,0.0008196111,0.001065293,0.001487577,0.0017621,0.0004482374],"domain_scores_gemma":[0.9930214,0.001143519,0.0004369602,0.002595923,0.002394289,0.0004078918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003870265,0.0003377231,0.001571489,0.001521141,0.0001339879,0.000112656,0.00008479498,0.005226652,0.001493306,0.002641395,0.9470786,0.03941112],"study_design_scores_gemma":[0.0004245117,0.000176858,0.007911243,0.0005964807,0.0000971281,0.0004317308,0.000363635,0.02109082,0.006483514,0.01389209,0.9483156,0.0002163884],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00366203,0.00108626,0.01474207,0.0008141314,0.0007126522,0.0009660902,0.9579521,0.01530807,0.004756544],"genre_scores_gemma":[0.003325475,0.0002447498,0.02251605,0.0002315797,0.000048442,0.001480903,0.9701351,0.0005680025,0.001449637],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02200195,"threshold_uncertainty_score":0.07360387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09582514426084024,"score_gpt":0.3052760271982961,"score_spread":0.2094508829374558,"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."}}