{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001359605,0.0002420818,0.0003817814,0.0002786152,0.0003585355,0.0001329653,0.001110733,0.0001380371,0.0001957694],"category_scores_gemma":[0.00008981274,0.0002792859,0.0002310037,0.0005466433,0.00007478058,0.0008249204,0.001098457,0.0003555791,0.000002281578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000205004,"about_ca_system_score_gemma":0.0002598233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001373203,"about_ca_topic_score_gemma":0.00002732129,"domain_scores_codex":[0.998068,0.0002575532,0.0002793393,0.0009308037,0.0002252064,0.0002391302],"domain_scores_gemma":[0.9979261,0.00006427825,0.0006251127,0.0008341733,0.0004788205,0.00007152194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008348746,0.0001570483,0.002501128,0.0002679924,0.0001455463,0.00000917382,0.0006761508,0.9542584,0.0009179225,0.007876352,0.00002311826,0.0330837],"study_design_scores_gemma":[0.0001981881,0.0002152989,0.0001568398,0.00009422887,0.0001777432,0.000002330667,0.0001365871,0.9877906,0.0020694,0.008613963,0.0002592533,0.0002855806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2628371,0.0001882547,0.7324541,0.00003743654,0.000132369,0.0007319385,0.00005765774,0.0004590541,0.003102093],"genre_scores_gemma":[0.9858764,0.00003706412,0.01300248,0.000008110186,0.0000425906,0.0000068071,0.0001426407,0.00001980595,0.0008641114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7230393,"threshold_uncertainty_score":0.9999659,"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."}}