{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008016472,0.0002884193,0.0004137817,0.0003859852,0.0002154115,0.0007013404,0.002845731,0.00008575705,0.00002371267],"category_scores_gemma":[0.001000104,0.0002344174,0.0001088345,0.002411898,0.00008224989,0.0005421005,0.001330059,0.0002944971,0.00003841627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008716093,"about_ca_system_score_gemma":0.0001263724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006709107,"about_ca_topic_score_gemma":0.000147851,"domain_scores_codex":[0.9976844,0.00001551716,0.0005737648,0.0007193945,0.0004756482,0.0005312663],"domain_scores_gemma":[0.9987026,0.00005981832,0.0002406538,0.0004223904,0.0004455745,0.0001289497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003170351,0.0002982715,0.001439385,0.0001418103,0.00007476762,0.000004013931,0.006058694,0.01676155,0.1131734,0.6308751,0.001892815,0.2289632],"study_design_scores_gemma":[0.00003045808,0.0001905563,0.0002462844,0.0005553226,0.00001721273,0.000003761626,0.0003631656,0.7695544,0.1940115,0.03438224,0.0003118906,0.000333166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5307941,0.00004335196,0.3952183,0.05696757,0.0005083974,0.001834722,0.00008511316,0.0003059771,0.01424247],"genre_scores_gemma":[0.9773187,0.000004186683,0.02035066,0.0005637279,0.00003644784,0.00003500551,0.000001786875,0.0000128572,0.00167662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7527929,"threshold_uncertainty_score":0.9559262,"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."}}