{"id":"W4238781109","doi":"10.31234/osf.io/nesuq","title":"Encoding structure in holographic reduced representations","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Carleton University","funders":"","keywords":"Encoding (memory); Decoding methods; Content-addressable memory; Shuffling; ENCODE; Computer science; Associative property; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Algorithm; Mathematics; Artificial neural network; Biology; Pure 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004235424,0.0002948688,0.0004428563,0.0006929451,0.0003062556,0.001586001,0.0007148004,0.000616025,0.004350031],"category_scores_gemma":[0.002446108,0.0003007453,0.0004489787,0.0005366481,0.001636423,0.003559555,0.001147425,0.0009034752,0.0007036414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005779477,"about_ca_system_score_gemma":0.000375684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006757446,"about_ca_topic_score_gemma":0.000624464,"domain_scores_codex":[0.9995998,0.0001401858,0.00002886417,0.00007826233,0.0001070865,0.00004587923],"domain_scores_gemma":[0.999234,0.0003044402,0.0001205808,0.0001906821,0.000111288,0.00003908118],"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":[0.00006292497,0.00001970475,0.0001397065,0.00007256219,0.00001350377,0.00007441668,0.00017494,0.02762815,0.007221929,0.9330296,0.001024168,0.03053844],"study_design_scores_gemma":[0.00001666771,0.0000428399,0.0001457838,0.00001857661,0.000006345608,0.00007106537,0.00006183482,0.195356,0.003567465,0.7976338,0.003060023,0.00001958563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1849125,0.000640113,0.7916477,0.0007854385,0.0001222727,0.00005658577,0.0003923021,0.0006069503,0.02083625],"genre_scores_gemma":[0.8617726,0.0006700257,0.1245443,0.0002601992,0.0001101721,0.0001120053,0.0004275925,0.0002190972,0.01188411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004350031,"threshold_uncertainty_score":0.0145523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02774963516039623,"score_gpt":0.2986585870542886,"score_spread":0.2709089518938924,"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."}}