{"id":"W4392231600","doi":"10.1007/s10044-024-01213-y","title":"Big topic modeling based on a two-level hierarchical latent Beta-Liouville allocation for large-scale data and parameter streaming","year":2024,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scale (ratio); BETA (programming language); Big data; Artificial intelligence; Data mining; Physics","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":[0.0002777782,0.0001051781,0.0001575357,0.0002105692,0.0001573113,0.000271199,0.0003337922,0.00003483807,0.000003666491],"category_scores_gemma":[0.0000067504,0.00009114296,0.00006446286,0.0003740189,0.00001154909,0.0001116693,0.0001789995,0.00008745331,0.000002397111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470139,"about_ca_system_score_gemma":0.000020988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001028923,"about_ca_topic_score_gemma":0.000267485,"domain_scores_codex":[0.9987924,0.00002440969,0.0002207965,0.0006624481,0.0001382561,0.0001616675],"domain_scores_gemma":[0.9989305,0.0001567073,0.00003104828,0.0007762495,0.00003267517,0.0000727867],"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":[0.000001643261,0.00009122588,0.005544691,0.00007008598,0.0002109177,7.14628e-7,0.0002923077,0.03429198,0.0001399801,0.01098765,0.00001339792,0.9483554],"study_design_scores_gemma":[0.0001364321,0.000009642027,0.0007275777,0.00001638578,0.0001985916,5.031838e-7,0.00001500824,0.9969414,0.00003694751,0.001206762,0.0006072329,0.0001035279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01940753,0.0001670344,0.9778864,0.00208953,0.00002234185,0.0002282169,0.0001155185,0.00005713856,0.00002630654],"genre_scores_gemma":[0.9437569,0.00002396514,0.0554008,0.0003139851,0.00009089994,0.0001786945,0.0001918726,0.000007075337,0.00003584033],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9626494,"threshold_uncertainty_score":0.3716702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07047955069751044,"score_gpt":0.3082657168572723,"score_spread":0.2377861661597618,"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."}}