{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.001204474,0.0001048689,0.0001049099,0.0002404003,0.00358379,0.0009050377,0.003473928,0.00002231959,0.00045663],"category_scores_gemma":[0.0004719146,0.0001227098,0.00001703373,0.0006637662,0.00007595935,0.0007629738,0.01303042,0.0002478662,0.0002196135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001824111,"about_ca_system_score_gemma":0.000006480007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007150932,"about_ca_topic_score_gemma":1.999428e-7,"domain_scores_codex":[0.9979551,0.000282957,0.0002018117,0.0007141809,0.0004612186,0.0003847622],"domain_scores_gemma":[0.9982431,0.00006532464,0.00009012907,0.001271662,0.0001821605,0.000147606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005854415,0.0001347863,0.000002318534,0.00009224469,0.00002855151,0.00001530829,0.0005712313,0.0008628762,0.002679906,0.007121782,0.1079081,0.8805243],"study_design_scores_gemma":[0.0003284358,0.0001152951,0.0001161285,0.000003269376,0.00000261082,0.0001133468,0.00009785257,0.3723394,0.00002319824,0.0001751597,0.626591,0.00009431483],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007037469,0.0001190496,0.992782,0.001523438,0.0001409733,0.0006709935,0.001532975,0.0006622702,0.001864527],"genre_scores_gemma":[0.7469893,0.000422831,0.1907544,0.000941203,0.0005800194,0.000003319864,0.05505941,0.003546355,0.001703283],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.88043,"threshold_uncertainty_score":0.9977134,"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."}}