{"id":"W4393700520","doi":"10.5281/zenodo.7812051","title":"Data from: The problem with missingness in mixed-type datasets and what we can do about it","year":2023,"lang":"en","type":"dataset","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":"University of Guelph","funders":"","keywords":"Missing data; Type (biology); Computer science; Data type; Data science; Data mining; Statistics; Mathematics; Machine learning; Geology; Programming language","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","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.001397716,0.000328661,0.000307308,0.0003243478,0.001558848,0.007680814,0.009705938,0.0001370542,0.0004525853],"category_scores_gemma":[0.0005990326,0.0002615055,0.00001753734,0.001712207,0.0003515975,0.00173393,0.0183198,0.001003063,0.004221348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001701142,"about_ca_system_score_gemma":0.00004018049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004967874,"about_ca_topic_score_gemma":0.0001392203,"domain_scores_codex":[0.9958328,0.0007079891,0.0003680125,0.001432714,0.0009844485,0.0006740452],"domain_scores_gemma":[0.9953558,0.0002270532,0.0001914845,0.00363871,0.0003381027,0.0002487858],"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":[0.00003163638,0.00004802832,1.649933e-7,0.0001156496,0.00003838402,0.0001568658,0.0003247274,0.00006188072,0.0000128684,0.00002501655,0.8921778,0.107007],"study_design_scores_gemma":[0.0004275285,0.00014118,0.00007049214,0.0006829295,0.00001418045,0.0001064076,0.000400644,0.002493854,0.000004725029,0.0001167305,0.9952249,0.0003164599],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002533614,0.0009399967,0.002907623,0.005521331,0.0002004983,0.0007643105,0.9891305,0.0003947681,0.0001156191],"genre_scores_gemma":[0.00002382869,0.005942431,0.002124517,0.0001801456,0.0001449711,1.921098e-7,0.9906659,0.0007576192,0.0001603567],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1066905,"threshold_uncertainty_score":0.9999837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0762632156264673,"score_gpt":0.306553596723691,"score_spread":0.2302903810972237,"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."}}