{"id":"W2970259172","doi":"10.18653/v1/d19-1349","title":"Evaluating Topic Quality with Posterior Variability","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Natural language processing; Joint (building); Quality (philosophy); Artificial intelligence; Engineering; Philosophy; Epistemology","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":[0.00120216,0.00007078908,0.0001154086,0.00001717792,0.00003321306,0.00007819875,0.0004281924,0.00002794972,0.0001814875],"category_scores_gemma":[0.00005673954,0.00005066971,0.00002300115,0.00009927392,0.000009067585,0.000285261,0.0001919668,0.000070879,0.00009405805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003298056,"about_ca_system_score_gemma":0.00007119471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001097432,"about_ca_topic_score_gemma":0.00001093477,"domain_scores_codex":[0.9988893,0.00013885,0.0001810214,0.0003666013,0.0002640918,0.0001601298],"domain_scores_gemma":[0.9988347,0.0001306574,0.00004774771,0.0008738482,0.00007158091,0.00004146789],"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":[0.00002222559,0.00009300646,0.2614315,0.0001225173,0.00002698042,0.000003037839,0.001800157,0.00188953,0.0120139,0.3933479,0.00001451779,0.3292348],"study_design_scores_gemma":[0.001082114,0.0003641801,0.1595788,0.00003552667,0.00000613069,0.00002017535,0.00007560007,0.8214273,0.002488953,0.01417573,0.0002943385,0.0004511425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5848793,0.00000210199,0.403583,0.000406744,0.000114786,0.0001172364,9.941281e-8,0.000085932,0.01081078],"genre_scores_gemma":[0.7587661,5.540129e-8,0.2398258,0.0003283084,0.00001854076,0.000003765234,1.817803e-7,0.000002127683,0.001055135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8195378,"threshold_uncertainty_score":0.2066251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08068371065089569,"score_gpt":0.3653743833317343,"score_spread":0.2846906726808386,"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."}}