{"id":"W2913881722","doi":"10.1098/rsta.2019.0162","title":"A semi-holographic hyperdimensional representation system for hardware-friendly cognitive computing","year":2019,"lang":"en","type":"article","venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Operand; Cognitive computing; Cognition; Representation (politics); Knowledge representation and reasoning; Artificial intelligence; Cognitive architecture; Multiplication (music); Microprocessor; Associative property; Theoretical computer science; Computer hardware; 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":[0.000150366,0.000144709,0.0002627061,0.00002098733,0.0002113515,0.00001957239,0.0001448569,0.00005368362,0.00000285091],"category_scores_gemma":[0.0000322232,0.0001019178,0.0002825753,0.0002911931,0.0002101814,0.00009496414,0.00002164233,0.0002173575,0.000002128413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001527686,"about_ca_system_score_gemma":0.000006307614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.662072e-7,"about_ca_topic_score_gemma":1.633874e-8,"domain_scores_codex":[0.9991331,0.0000141444,0.000202851,0.0002185136,0.0002158955,0.0002155305],"domain_scores_gemma":[0.999004,0.0007697474,0.00003430281,0.00009405031,0.00003478982,0.00006307388],"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":[0.0000130628,0.00008203882,0.00002303443,0.001100002,0.00009276106,2.620371e-7,0.0004327196,0.9609989,0.0159092,0.02032933,0.000004046834,0.00101466],"study_design_scores_gemma":[0.0002475657,0.00008945225,0.0001744971,0.0002868277,0.00004996826,0.000007007938,0.0001674852,0.9795278,0.008510755,0.0108004,0.000002636026,0.0001355599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6951771,0.00003590385,0.303964,0.0001489463,0.0001405022,0.0002354609,0.00001092049,0.0001336041,0.0001536011],"genre_scores_gemma":[0.9964646,0.000001581987,0.003402352,0.00001290024,0.00008490035,0.00001370829,6.065291e-7,0.0000129527,0.000006410338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3012875,"threshold_uncertainty_score":0.4156086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01870849569722435,"score_gpt":0.2500882900161636,"score_spread":0.2313797943189393,"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."}}