{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016075,0.0002515422,0.0003370431,0.0001478654,0.0001146901,0.00008960044,0.001144582,0.0001841698,0.00002151421],"category_scores_gemma":[0.00006988534,0.0003088322,0.0001489707,0.0006681299,0.000129064,0.0003777245,0.00104066,0.0008584612,0.00001257828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192316,"about_ca_system_score_gemma":0.0001089475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009677649,"about_ca_topic_score_gemma":0.000009948298,"domain_scores_codex":[0.9983062,0.0002380931,0.0002460816,0.0008633969,0.00008555931,0.0002606464],"domain_scores_gemma":[0.9986581,0.0001039392,0.0004253761,0.0004513328,0.0002123942,0.0001489062],"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":[0.0001337822,0.00007288237,0.0006797586,0.00005160167,0.0001432625,0.00006586853,0.002190339,0.9169269,0.001104828,0.06900923,0.002229818,0.007391723],"study_design_scores_gemma":[0.0003505298,0.000117191,0.0002158583,0.00006201881,0.00002790218,0.000005144795,0.0003016436,0.9954942,0.0002618949,0.002727177,0.0001548089,0.0002816662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04753005,0.00007963933,0.9495881,0.000177621,0.0005731411,0.0001767156,0.000005922982,0.0001974035,0.001671404],"genre_scores_gemma":[0.9981045,0.00003955216,0.001094847,0.00007013964,0.00006635457,7.063579e-7,0.00002512979,0.00001393396,0.0005848671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9505744,"threshold_uncertainty_score":0.9999364,"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."}}