{"id":"W3037078219","doi":"","title":"Reliability of Perplexity to Find Number of Latent Topics.","year":2020,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Perplexity; Computer science; Reliability (semiconductor); Natural language processing; Language model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01400445,0.001455499,0.00154532,0.008782848,0.0006804165,0.002316897,0.001369011,0.00172283,0.003334231],"category_scores_gemma":[0.08247761,0.0005378546,0.001482069,0.004292264,0.0008814339,0.002628709,0.001817888,0.002629002,0.003197067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009513565,"about_ca_system_score_gemma":0.0008265392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004016488,"about_ca_topic_score_gemma":0.002798822,"domain_scores_codex":[0.9888585,0.006019808,0.0007532432,0.002166019,0.001652323,0.0005501275],"domain_scores_gemma":[0.9212006,0.06262065,0.002519202,0.007557748,0.004972319,0.001129565],"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":[0.00373346,0.0004678316,0.3913461,0.001397917,0.003340008,0.0004064258,0.002392217,0.09299412,0.01482892,0.008114137,0.03274977,0.448229],"study_design_scores_gemma":[0.0001367027,0.0005850176,0.1530738,0.0003098106,0.000709149,0.0008757081,0.0006672469,0.7991406,0.01255583,0.02586774,0.005851359,0.0002269821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5377262,0.005045307,0.4234024,0.001040901,0.000560914,0.0004956674,0.01514929,0.005671147,0.01090815],"genre_scores_gemma":[0.9688355,0.0003815604,0.02252626,0.00007818604,0.0002050475,0.0002444525,0.006243775,0.0003983666,0.001086749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01400445,"threshold_uncertainty_score":0.07406354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0205574233174598,"score_gpt":0.2490113041657319,"score_spread":0.2284538808482721,"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."}}