{"id":"W7161205419","doi":"","title":"Context is Key: A Benchmark for Forecasting with Essential Textual Information","year":2024,"lang":"","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Office of Science; Mitacs; U.S. Department of Energy","keywords":"Benchmark (surveying); Context (archaeology); Task (project management); Time series; Range (aeronautics); Variety (cybernetics); Series (stratigraphy)","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":[0.004530535,0.002053643,0.0009089118,0.002855464,0.0009971643,0.002477084,0.001950357,0.002225835,0.00577123],"category_scores_gemma":[0.03602849,0.0003595178,0.0008231343,0.002810419,0.0006633536,0.004679516,0.002171363,0.002300477,0.002682006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001316301,"about_ca_system_score_gemma":0.001808939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01092027,"about_ca_topic_score_gemma":0.01120643,"domain_scores_codex":[0.9973519,0.001031304,0.0002667153,0.0006210189,0.0005835201,0.0001455948],"domain_scores_gemma":[0.9886239,0.007481068,0.0006336853,0.001613681,0.001203886,0.0004438574],"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":[0.002281751,0.0007606284,0.01704204,0.002396607,0.000287698,0.0005146709,0.0006049062,0.3280498,0.01003676,0.02384797,0.1142363,0.4999409],"study_design_scores_gemma":[0.0001191497,0.0002316179,0.003075063,0.0002030118,0.00005871002,0.0001107184,0.0003579909,0.9392319,0.008297466,0.0246113,0.02361971,0.00008326276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2730358,0.01478105,0.5502874,0.008802947,0.004077984,0.0007906906,0.05328004,0.05396798,0.04097619],"genre_scores_gemma":[0.5755749,0.00201356,0.3748083,0.0006813373,0.0004172505,0.0004970567,0.04055767,0.001924134,0.003525833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01092027,"threshold_uncertainty_score":0.02396005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03255876441735268,"score_gpt":0.2927016363932953,"score_spread":0.2601428719759427,"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."}}