{"id":"W2963221401","doi":"","title":"Variational Memory Addressing in Generative Models","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Generative grammar; Generative model; Memory model; Inference; Artificial intelligence; Adaptive memory; Memory address; Flat memory model; Machine learning; Theoretical computer science; Memory management; Semiconductor memory; Shared memory; Parallel computing; Cognition","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004996567,0.00007974714,0.0001085876,0.00006759826,0.001720055,0.001444243,0.0002315841,0.00009341659,0.0000174084],"category_scores_gemma":[0.0001850063,0.00006671601,0.00002470526,0.00008830742,0.00009011335,0.01049365,0.00002661882,0.0001085147,0.00002389373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001492486,"about_ca_system_score_gemma":0.0001710947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003026586,"about_ca_topic_score_gemma":0.0004719401,"domain_scores_codex":[0.9989359,0.00009022044,0.0003040153,0.00008604726,0.0003869911,0.0001967744],"domain_scores_gemma":[0.9991821,0.0000145634,0.0003985821,0.000115814,0.0002375805,0.00005137414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007787674,0.00007512634,0.002886869,0.0005146567,0.00002595571,0.00001224882,0.4938722,0.1308907,0.0006408488,0.1344414,0.00419069,0.2323714],"study_design_scores_gemma":[0.0007385123,0.0000158044,0.004605288,0.0003150534,0.000009441596,0.000007868188,0.03282163,0.9551224,0.0000726108,0.001488278,0.004469163,0.0003339683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4363463,0.001731007,0.02659846,0.006236326,0.003911652,0.001838001,0.00003531329,0.0005198839,0.522783],"genre_scores_gemma":[0.9984261,0.000007297047,0.0001655236,0.0001776297,0.0003440068,0.00003484499,0.00002345687,0.000003140636,0.0008179356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8242317,"threshold_uncertainty_score":0.9995924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08099046346303104,"score_gpt":0.3427947311512652,"score_spread":0.2618042676882342,"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."}}