{"id":"W3124818821","doi":"10.48550/arxiv.2101.07528","title":"The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels\\n Methods","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Kernel (algebra); Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Feature extraction; Representation (politics); Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.000842021,0.000213111,0.0003270034,0.00009554258,0.0001608454,0.00005471661,0.001669684,0.0001692158,0.000004747316],"category_scores_gemma":[0.0001069265,0.0002083059,0.000164214,0.001040531,0.0002163474,0.0002419544,0.00202307,0.0004928379,0.000004887108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002495964,"about_ca_system_score_gemma":0.000249967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000126861,"about_ca_topic_score_gemma":0.0001103325,"domain_scores_codex":[0.9976251,0.000937051,0.0002168758,0.000836632,0.00008685384,0.0002975324],"domain_scores_gemma":[0.9959841,0.002322857,0.0002469167,0.001150335,0.0002194606,0.00007627018],"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":[0.00002945706,0.00008085269,0.004811137,0.0000743804,0.00005162651,0.00004214639,0.00007269489,0.577511,0.0003481805,0.4141181,0.000005314694,0.0028551],"study_design_scores_gemma":[0.0003970559,0.00002104071,0.03528581,0.0001732138,0.00002853977,0.000005272634,0.0001042453,0.7101534,0.002702354,0.2505699,0.000236339,0.0003228351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1233521,0.000540317,0.8750511,0.00004953378,0.0002367035,0.0003251907,0.000003596361,0.00005939814,0.0003820279],"genre_scores_gemma":[0.9721376,0.000371908,0.0272701,0.00001520324,0.00002017516,0.000009594607,0.00001115322,0.00001109094,0.0001531433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8487856,"threshold_uncertainty_score":0.8494469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06143092665756005,"score_gpt":0.2423320159858164,"score_spread":0.1809010893282564,"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."}}