{"id":"W3110297414","doi":"","title":"Contextual Interference Reduction by Selective Fine-Tuning of Neural Networks.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Interpretability; Robustness (evolution); Artificial intelligence; MNIST database; Machine learning; Feature learning; Artificial neural network; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004280022,0.0009967516,0.0005247831,0.0003614548,0.0002624182,0.0004388619,0.001372642,0.0007049462,0.001212311],"category_scores_gemma":[0.002460718,0.0002901318,0.0005319613,0.000383019,0.000489969,0.0009861698,0.001158243,0.001282031,0.0004361215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005835406,"about_ca_system_score_gemma":0.0004983161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002103546,"about_ca_topic_score_gemma":0.004865838,"domain_scores_codex":[0.9997695,0.00004760151,0.000009581921,0.00009140008,0.00004522648,0.00003679784],"domain_scores_gemma":[0.9995626,0.0001625264,0.000051238,0.0001186419,0.00006741302,0.00003759443],"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":[0.0003513411,0.0003976571,0.001736784,0.0003030831,0.0002068791,0.0001929229,0.0001890114,0.3787569,0.1714084,0.00826816,0.004140792,0.4340481],"study_design_scores_gemma":[0.00001534502,0.00007710987,0.0008059652,0.00001329134,0.00003496375,0.00005584331,0.00002192935,0.9648981,0.02516418,0.007267924,0.001635103,0.00001022012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09219984,0.0008819903,0.9003598,0.0001840793,0.0001046108,0.00008784021,0.0001335568,0.002780444,0.003267954],"genre_scores_gemma":[0.8092007,0.0002971119,0.1871454,0.0002829869,0.00006492752,0.0001407416,0.0003758258,0.0002558673,0.002236431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002103546,"threshold_uncertainty_score":0.004233956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0754647525756441,"score_gpt":0.1973286408512761,"score_spread":0.121863888275632,"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."}}