{"id":"W7107967301","doi":"10.5281/zenodo.17764937","title":"Regularization Strategies for Neural Inverse Problems: A Comparative Study","year":2025,"lang":"","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Numerical methods in inverse problems","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Tikhonov regularization; Regularization (linguistics); Inverse problem; Artificial neural network; Regularization perspectives on support vector machines; Backus–Gilbert method","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":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004491967,0.001053194,0.001492269,0.0009524298,0.005280628,0.004176845,0.003788581,0.000551525,0.006082654],"category_scores_gemma":[0.004067509,0.001171431,0.0004204375,0.001840782,0.0008061723,0.0008034763,0.008147326,0.001908095,0.001467932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009186981,"about_ca_system_score_gemma":0.00008563939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005659926,"about_ca_topic_score_gemma":0.000003994565,"domain_scores_codex":[0.9886863,0.004633023,0.001985033,0.002262982,0.00121693,0.001215789],"domain_scores_gemma":[0.9911578,0.000703545,0.001422695,0.002223102,0.004047311,0.0004455203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00240179,0.01179705,0.00001239304,0.0173613,0.004389802,0.00004754618,0.1742943,0.04665378,0.004076135,0.2960982,0.3208771,0.1219906],"study_design_scores_gemma":[0.004672389,0.003138406,0.00003004654,0.001148338,0.0009735091,0.00005245202,0.04391118,0.1305987,0.0003600563,0.2093926,0.6039833,0.0017391],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009973904,0.0002154989,0.7708208,0.001215632,0.002033719,0.02945143,0.003362282,0.003483562,0.1794432],"genre_scores_gemma":[0.4809688,0.0006479194,0.446652,0.0009357973,0.002257416,0.00004302357,0.01794033,0.01747292,0.03308186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4709949,"threshold_uncertainty_score":0.9998746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1895800848370779,"score_gpt":0.3706155287190798,"score_spread":0.1810354438820018,"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."}}