{"id":"W4312072439","doi":"10.1214/22-aos2229","title":"Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations","year":2022,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Estimator; Minimax; Applied mathematics; Context (archaeology); Matrix (chemical analysis); Combinatorics; Multinomial distribution; Matrix norm; Statistics; Eigenvalues and eigenvectors; Mathematical optimization","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":[0.0003762445,0.00006648245,0.0001319836,0.00005973284,0.0001313824,0.00001799536,0.0003126458,0.00001428711,0.000005632356],"category_scores_gemma":[0.00004810769,0.00005896505,0.00001965792,0.0003638421,0.00002522508,0.0001115369,0.0001946242,0.00008017996,5.312359e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002171907,"about_ca_system_score_gemma":0.00004919549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004853456,"about_ca_topic_score_gemma":0.00002989869,"domain_scores_codex":[0.9991515,0.0001036839,0.0002778475,0.0001512677,0.0001833707,0.0001322779],"domain_scores_gemma":[0.9992439,0.000191225,0.0001091486,0.000313856,0.00009367025,0.00004819825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002783563,0.00004508933,0.00001170148,0.00001981763,0.000005647339,4.999398e-7,0.0007410827,0.02280748,0.00007549208,0.9376302,0.0001501555,0.03851008],"study_design_scores_gemma":[0.0000863304,0.00004921125,0.0008732511,0.00001052138,0.000007326214,0.000001262995,0.00003563943,0.3881383,0.0005314849,0.6098167,0.0003880428,0.00006190248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005911399,0.0002482494,0.9902484,0.002720011,0.0000280677,0.0003524593,0.0003658603,0.00000886659,0.0001167321],"genre_scores_gemma":[0.7178592,0.00004206205,0.2818373,0.00008593012,0.000005316806,0.0001006308,0.00001640998,0.000002587723,0.0000505249],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7119478,"threshold_uncertainty_score":0.2404525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06472341957351041,"score_gpt":0.3489276257576649,"score_spread":0.2842042061841545,"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."}}