{"id":"W4409363931","doi":"10.1609/aaai.v39i19.34224","title":"Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia; HORIZON EUROPE Framework Programme; European Commission","keywords":"Series (stratigraphy); Time series; Computer science; Artificial intelligence; Machine learning; Data mining; Geology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06232302,0.002038477,0.002777363,0.004019406,0.001907403,0.006127466,0.00321599,0.003979617,0.00193377],"category_scores_gemma":[0.2737337,0.001068943,0.001478998,0.003900593,0.002154926,0.01245407,0.003511618,0.005154202,0.001721551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001316081,"about_ca_system_score_gemma":0.002648258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002575281,"about_ca_topic_score_gemma":0.003385173,"domain_scores_codex":[0.9696408,0.02181752,0.001768169,0.002805946,0.003404476,0.0005630195],"domain_scores_gemma":[0.8421885,0.1144018,0.008362076,0.02239597,0.01068516,0.001966483],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00278106,0.001099904,0.0894208,0.002045711,0.001220716,0.0004171009,0.0025208,0.1205092,0.008582003,0.03684091,0.07544374,0.659118],"study_design_scores_gemma":[0.001392802,0.001901948,0.02987254,0.003931594,0.0005373246,0.0006444542,0.003968202,0.6037371,0.02146482,0.2803459,0.05146805,0.0007352356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2273768,0.009383584,0.6991372,0.04115257,0.001837298,0.002171082,0.004989407,0.004659078,0.009293099],"genre_scores_gemma":[0.4805251,0.002026937,0.5061094,0.004003822,0.0005777101,0.001510468,0.003692726,0.0006104847,0.0009433017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.937677,"threshold_uncertainty_score":0.3295996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08945305177106444,"score_gpt":0.2955514333811198,"score_spread":0.2060983816100553,"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."}}