{"id":"W4409921220","doi":"10.1016/j.patter.2025.101242","title":"Fine-Pruning: A biologically inspired algorithm for personalization of machine learning models","year":2025,"lang":"en","type":"article","venue":"Patterns","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Pruning; Personalization; Computer science; Artificial intelligence; Machine learning; Algorithm; World Wide Web; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001235275,0.00007743195,0.0001115468,0.00007739515,0.0001288566,0.00002272712,0.000341242,0.00004345667,0.00000788322],"category_scores_gemma":[0.00002037394,0.00006979191,0.00005981823,0.0002521351,0.00001996849,0.0001354373,0.0001135716,0.00006275691,0.000001522484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001865462,"about_ca_system_score_gemma":0.00003544126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005075312,"about_ca_topic_score_gemma":0.000007584611,"domain_scores_codex":[0.9993587,0.0000283539,0.0001779477,0.0002289233,0.00008055099,0.0001255213],"domain_scores_gemma":[0.9995242,0.00008839939,0.00007812308,0.0001722811,0.0001120201,0.00002499656],"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":[0.000007713136,0.0003851014,0.01840396,0.0001304571,0.00008433131,0.000001612473,0.0009984603,0.01482364,0.003374878,0.4061666,0.0004165242,0.5552068],"study_design_scores_gemma":[0.0002338473,0.00005539578,0.002992342,0.00002688145,0.000005348077,0.00000101498,0.00001432904,0.9838743,0.0003518148,0.01103242,0.001340727,0.00007153142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004197385,0.0001579876,0.9940938,0.0008683416,0.00005480371,0.0001912414,0.00003865312,0.00008383981,0.0003139023],"genre_scores_gemma":[0.7583022,0.00002855032,0.2405373,0.0001645286,0.00003285476,0.0001254057,0.00008950142,0.000005179264,0.0007144491],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9690507,"threshold_uncertainty_score":0.2846031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03328274057532203,"score_gpt":0.2683327428698241,"score_spread":0.235050002294502,"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."}}