{"id":"W4389260608","doi":"10.48550/arxiv.2311.18010","title":"Active learning meets fractal decision boundaries: a cautionary tale from the Sitnikov three-body problem","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"HORIZON EUROPE Framework Programme; Alliance de recherche numérique du Canada; European Commission; Canada Research Chairs; Flatiron Health","keywords":"Fractal; Chaotic; Context (archaeology); Boundary (topology); Stability (learning theory); Cosmology; Computer science; Gravitation; Attractor; Cluster (spacecraft); Artificial intelligence; Decision boundary; Three-body problem; Physics; Astrophysics; Astronomy; Mathematics; Machine learning; Geography; Mathematical analysis","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0004778769,0.0004363354,0.0003921993,0.0001932144,0.001422512,0.0007126749,0.002582869,0.0003531355,0.00007211921],"category_scores_gemma":[0.0002180062,0.000388856,0.0003045489,0.0007792664,0.0002998435,0.0005057995,0.004449607,0.002177588,0.0004182453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002527525,"about_ca_system_score_gemma":0.0005815036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003987834,"about_ca_topic_score_gemma":0.0005215377,"domain_scores_codex":[0.9970582,0.0003517087,0.0002602714,0.001547405,0.0002981916,0.0004841938],"domain_scores_gemma":[0.9969365,0.001112391,0.0004035186,0.001201043,0.0001804533,0.0001660838],"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":[0.0002193529,0.0002541847,0.0177624,0.00006105544,0.0006970951,0.001749157,0.00620819,0.8530399,0.00006990809,0.07919765,0.003222803,0.0375183],"study_design_scores_gemma":[0.0004792628,0.0000844417,0.02131803,0.0002229796,0.00007632015,0.000007122781,0.0003146081,0.8505318,0.00001599224,0.1165197,0.009897444,0.0005323632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2784383,0.00009311384,0.7170126,0.001169912,0.001153619,0.0003893683,0.00005317797,0.0008094054,0.0008804738],"genre_scores_gemma":[0.991475,0.00007661484,0.005587352,0.00008784507,0.0002815424,0.000003830846,0.0001189042,0.00004006831,0.002328787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7130368,"threshold_uncertainty_score":0.9998775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04102123877156246,"score_gpt":0.2044157639452436,"score_spread":0.1633945251736811,"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."}}