{"id":"W4381161845","doi":"10.20944/preprints202306.1378.v1","title":"Algorithm-based Data Generation (ADG) Engine for Data Analytics","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Big data; Computer science; Analytics; Data analysis; Domain (mathematical analysis); Data science; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005048369,0.001510627,0.001049247,0.003717253,0.0008846738,0.002985111,0.002801801,0.001221424,0.005664958],"category_scores_gemma":[0.01602104,0.0007249131,0.00154305,0.004394833,0.0009203636,0.002729772,0.002584711,0.002516177,0.005265574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107155,"about_ca_system_score_gemma":0.001849648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001785441,"about_ca_topic_score_gemma":0.001989289,"domain_scores_codex":[0.996624,0.0008682876,0.0004644549,0.0006578834,0.001256536,0.0001288832],"domain_scores_gemma":[0.9924345,0.003151143,0.0002936719,0.002583847,0.00133591,0.0002009508],"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":[0.0008101422,0.0004653389,0.008395842,0.001119265,0.0003733178,0.0005388117,0.0005160973,0.05518362,0.01709349,0.06058708,0.1047422,0.7501747],"study_design_scores_gemma":[0.0002345128,0.0001674457,0.001809254,0.0001586191,0.00009212506,0.0007448777,0.0001756031,0.7300806,0.03890314,0.1105898,0.1169531,0.00009091797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003356236,0.0003778757,0.9646842,0.00037706,0.0001461297,0.000353974,0.002410859,0.02653716,0.001756579],"genre_scores_gemma":[0.04343504,0.0002570757,0.94655,0.0002494321,0.00006165152,0.0004695526,0.006750728,0.001202711,0.001023807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005664958,"threshold_uncertainty_score":0.02669865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5410040128402656,"score_gpt":0.4267004535432325,"score_spread":0.1143035592970331,"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."}}