{"id":"W2995426144","doi":"10.48550/arxiv.2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"ENCODE; Convolutional neural network; Computer science; Artificial intelligence; Set (abstract data type); Position (finance); Contrast (vision); Artificial neural network; Filter (signal processing); Deep learning; Pattern recognition (psychology); Computer vision","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":[0.00004084975,0.0001300617,0.0001024171,0.00006003903,0.0002234828,0.0001501186,0.0006500005,0.00006678185,0.000009172232],"category_scores_gemma":[0.0000169932,0.0001513105,0.00006703759,0.0009742714,0.00006329854,0.002978265,0.0002300886,0.0001892622,0.00006054543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007568895,"about_ca_system_score_gemma":0.00002513279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000271573,"about_ca_topic_score_gemma":0.000001545807,"domain_scores_codex":[0.9991815,0.00004560491,0.0001131282,0.0003394489,0.0000797735,0.000240514],"domain_scores_gemma":[0.9992006,0.00006270386,0.0001257541,0.0003095406,0.0001216704,0.000179762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001576441,0.00001257893,0.000434478,0.00000368716,0.000007859667,0.00001329219,0.00007939317,0.4571152,0.00007486109,0.5392669,0.0009316801,0.002044233],"study_design_scores_gemma":[0.0002985362,0.00004765667,0.0005828999,0.000002974446,0.000008085745,0.000007829,0.00004184443,0.9882258,0.00006447473,0.008035554,0.002520707,0.0001636151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.025489,0.00002213592,0.9695593,0.003813904,0.0001081586,0.000179222,0.000005129989,0.0002737468,0.0005493827],"genre_scores_gemma":[0.995775,0.0000239951,0.002630975,0.0013629,0.0001037197,0.000001354221,0.0000285422,0.000004919686,0.00006856468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.970286,"threshold_uncertainty_score":0.6170264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03836477917555642,"score_gpt":0.1652807220127223,"score_spread":0.1269159428371658,"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."}}