{"id":"W4387504521","doi":"10.1016/j.patcog.2023.110037","title":"A topic modeling and image classification framework: The Generalized Dirichlet variational autoencoder","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent Dirichlet allocation; Autoencoder; Topic model; Dirichlet distribution; Computer science; Covariance; Inference; Artificial intelligence; Generative model; Latent variable; Representation (politics); Benchmark (surveying); Code (set theory); Pattern recognition (psychology); Machine learning; Artificial neural network; Mathematics; Generative grammar; Statistics; Set (abstract data type); Boundary value problem","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":[0.0003632426,0.00008918564,0.00007753263,0.00008274327,0.0001788355,0.0002058302,0.000231683,0.00006459707,0.00003103624],"category_scores_gemma":[0.00007441718,0.00007182379,0.00003164841,0.0002352792,0.00001476765,0.0003354715,0.0001176568,0.0001407752,0.0001415864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002399032,"about_ca_system_score_gemma":0.00002089322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004348132,"about_ca_topic_score_gemma":0.000005583965,"domain_scores_codex":[0.9990056,0.00009219346,0.0001946162,0.0003110804,0.0002181705,0.0001784115],"domain_scores_gemma":[0.999432,0.0001100093,0.00006156995,0.0002758731,0.00008439711,0.00003618877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004824923,0.00004117328,0.002047892,0.0000489016,0.00003848464,0.000008610154,0.003440266,0.006872242,0.001158406,0.01500884,0.0004170634,0.9709133],"study_design_scores_gemma":[0.0001277092,0.000005407879,0.004848496,0.00002185456,0.000006242185,0.000005242844,0.00003261845,0.9214077,0.00002708115,0.07337475,0.00005332815,0.00008959596],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018278,0.00002253907,0.8923423,0.00499832,0.0002703338,0.000137383,0.000005519361,0.0002122408,0.0001834667],"genre_scores_gemma":[0.8491037,0.00007789062,0.1490476,0.001227506,0.0002963405,0.0001084779,0.00006451374,0.00001160886,0.00006229633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9708237,"threshold_uncertainty_score":0.2928889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08430624976072619,"score_gpt":0.2919918592378226,"score_spread":0.2076856094770964,"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."}}