{"id":"W2067541510","doi":"10.1016/j.ijforecast.2011.10.001","title":"Testing time series data compatibility for benchmarking","year":2011,"lang":"en","type":"article","venue":"International Journal of Forecasting","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Benchmarking; Compatibility (geochemistry); Series (stratigraphy); Computer science; Econometrics; Time series; Statistics; Data mining; Mathematics; Machine learning; Engineering; Economics","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":[],"consensus_categories":[],"category_scores_codex":[0.001256685,0.0000914081,0.0003152667,0.0001908464,0.00008077765,0.00008148843,0.0007326772,0.00002916654,0.0005552152],"category_scores_gemma":[0.000944452,0.00009413382,0.0001246297,0.0001154658,0.00003168974,0.0006761013,0.0001791703,0.00008417462,0.00001751785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006037073,"about_ca_system_score_gemma":0.00002223526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000211701,"about_ca_topic_score_gemma":0.00002290263,"domain_scores_codex":[0.998587,0.000009805951,0.000996027,0.0001932805,0.00007312965,0.0001407603],"domain_scores_gemma":[0.997874,0.0001616768,0.001287103,0.0002156046,0.0004134002,0.0000482805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006238605,0.0004495581,0.7548807,0.000134683,0.002541551,0.0001140563,0.003465557,0.001014958,0.0004046321,0.06510197,0.004287383,0.1669811],"study_design_scores_gemma":[0.002153888,0.0008959301,0.09794515,0.0005833172,0.0001118908,0.001010642,0.0005532791,0.7286969,0.0002597273,0.1145863,0.05238357,0.0008193971],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7767592,0.001440947,0.1475455,0.0005798476,0.004580808,0.0003979391,0.001288402,0.00005181387,0.06735554],"genre_scores_gemma":[0.9270288,0.000003079541,0.07200757,0.00002629019,0.0007442954,0.000001442877,0.00002763136,0.0000125693,0.0001483317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7276819,"threshold_uncertainty_score":0.6079218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2960590050499919,"score_gpt":0.273547270225132,"score_spread":0.02251173482485991,"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."}}