{"id":"W4415112137","doi":"10.48550/arxiv.2506.12648","title":"Glocal Smoothness: Line search and adaptive step sizes can help in theory too!","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Lipschitz continuity; Smoothness; Line search; Iterated function; Constant (computer programming); Conjugate gradient method; Gradient descent; Line (geometry)","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"],"consensus_categories":[],"category_scores_codex":[0.001043069,0.000367302,0.000489659,0.0002915438,0.0001151534,0.0001782694,0.001728512,0.0003431681,0.0000243192],"category_scores_gemma":[0.0003100963,0.0003530245,0.00009819502,0.0004593707,0.0003720743,0.0001913003,0.003897376,0.001096762,0.00004819304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000181951,"about_ca_system_score_gemma":0.0005782804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002375385,"about_ca_topic_score_gemma":0.001987875,"domain_scores_codex":[0.9970455,0.0004362293,0.0005194528,0.001105273,0.0003676772,0.0005258337],"domain_scores_gemma":[0.9977096,0.0007690276,0.0001039667,0.001073009,0.0002093996,0.0001349849],"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":[0.0002536171,0.0004642656,0.3122782,0.0004096792,0.0002282951,0.000388347,0.0191331,0.01423859,0.0003444744,0.1641515,0.0004392209,0.4876708],"study_design_scores_gemma":[0.0007627892,0.0008311208,0.2032678,0.003121075,0.0001049272,0.00002671511,0.008188455,0.5325625,0.06513555,0.1801307,0.002567331,0.00330104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.730341,0.001191801,0.262778,0.002374702,0.0009718261,0.0005634624,0.00002909271,0.0001825417,0.001567489],"genre_scores_gemma":[0.9914842,0.0002390793,0.005706972,0.0005781038,0.0001793467,0.00007304548,0.000005329426,0.0000168183,0.001717057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5183239,"threshold_uncertainty_score":0.9998922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07470622997993834,"score_gpt":0.3311479336693621,"score_spread":0.2564417036894238,"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."}}