{"id":"W4297811803","doi":"10.48550/arxiv.2209.05300","title":"An Evaluation of Low Overhead Time Series Preprocessing Techniques for Downstream Machine Learning","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Leukemia and Lymphoma Society of Canada","keywords":"Computer science; Overhead (engineering); Machine learning; Series (stratigraphy); Preprocessor; Artificial intelligence; Time series; Data mining; Sampling (signal processing); Channel (broadcasting); Kernel (algebra); Workload; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.003316747,0.001688756,0.0007489135,0.001573756,0.0006512533,0.001176272,0.002110517,0.001052845,0.00236828],"category_scores_gemma":[0.01662463,0.0003331673,0.000714125,0.002338234,0.0004353207,0.00247109,0.0008627693,0.001733716,0.001704615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009028392,"about_ca_system_score_gemma":0.001417415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004787961,"about_ca_topic_score_gemma":0.00433458,"domain_scores_codex":[0.9975798,0.0006522927,0.0002015128,0.0004759024,0.0008954189,0.0001950898],"domain_scores_gemma":[0.9917119,0.004940277,0.0005297536,0.001335668,0.001255072,0.0002274031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003534746,0.002389176,0.015381,0.0009944142,0.0003751866,0.000304895,0.0002613589,0.2091654,0.04299937,0.003284308,0.01383511,0.7074751],"study_design_scores_gemma":[0.0001095152,0.0007973801,0.005271638,0.00002652631,0.00005383037,0.0001126167,0.0001103362,0.9646071,0.02411329,0.001541262,0.003231791,0.00002481536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5011092,0.002453723,0.4578208,0.001390227,0.0008135631,0.0006786682,0.002393103,0.02685989,0.00648071],"genre_scores_gemma":[0.7021996,0.0006597916,0.2883852,0.0002494664,0.0002026552,0.0003049961,0.005114743,0.0006808986,0.002202662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004787961,"threshold_uncertainty_score":0.01754081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05785272328014543,"score_gpt":0.2209344982324263,"score_spread":0.1630817749522808,"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."}}