{"id":"W2138806976","doi":"10.1111/j.1756-8765.2010.01109.x","title":"Discovering Binary Codes for Documents by Learning Deep Generative Models","year":2010,"lang":"en","type":"article","venue":"Topics in Cognitive Science","topic":"Topic Modeling","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Generative model; Generative grammar; Artificial intelligence; Word (group theory); Binary number; Inference; Set (abstract data type); Code (set theory); Natural language processing; Filter (signal processing); Binary code; Associative property; Deep learning; Information retrieval; Machine learning; Mathematics; Arithmetic","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007833086,0.000133315,0.0001381754,0.0001472943,0.0003679076,0.0003088026,0.0009170898,0.00005027659,0.000008321201],"category_scores_gemma":[0.0003400439,0.0001293165,0.00003228189,0.0004020814,0.0002738959,0.001812004,0.0004459759,0.0003319543,0.000004502353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005673684,"about_ca_system_score_gemma":0.0001414501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004333472,"about_ca_topic_score_gemma":0.00006135135,"domain_scores_codex":[0.9983054,0.0000322302,0.0002045605,0.0006579731,0.000360364,0.0004394247],"domain_scores_gemma":[0.9992225,0.0001776247,0.00007499554,0.0002400254,0.0001928477,0.00009205854],"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":[0.00002970148,0.0002532532,0.01052106,0.00004574938,0.00002072049,0.00002651663,0.01567338,0.04059713,0.1713693,0.4342238,0.00006692234,0.3271724],"study_design_scores_gemma":[0.0003549553,0.00006139612,0.0004149563,0.00002647947,0.000002203625,0.000002957309,0.0002133456,0.9487738,0.0179532,0.03180412,0.0001918774,0.0002007092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3583979,0.00003350914,0.6383791,0.0001934521,0.0003611962,0.0001945312,0.000002816113,0.00003749429,0.002400018],"genre_scores_gemma":[0.9171417,0.00001055404,0.08205301,0.0001864765,0.00007617001,0.00005839935,0.000002391097,0.000005721964,0.0004656243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9081767,"threshold_uncertainty_score":0.5273372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03774018067284531,"score_gpt":0.3249539954884382,"score_spread":0.2872138148155929,"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."}}