{"id":"W6958345719","doi":"10.6084/m9.figshare.23733064","title":"Additional file 1 of Quality indices for topic model selection and evaluation: a literature review and case study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Selection (genetic algorithm); Topic model; Quality (philosophy); Feature selection; Model selection","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003814369,0.00003674011,0.00009869803,0.00004486058,0.0002006905,0.00002997089,0.00002699714,0.00002616864,0.6545787],"category_scores_gemma":[0.003777068,0.00003343798,0.00002818992,0.0004103455,0.000005661989,0.00009315192,0.00001953154,0.00003162204,0.000007087142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001033773,"about_ca_system_score_gemma":0.000104943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001908955,"about_ca_topic_score_gemma":0.0005443482,"domain_scores_codex":[0.9993317,0.0002038928,0.0001101068,0.0001160359,0.0001866602,0.00005158744],"domain_scores_gemma":[0.9979312,0.001593396,0.00008077762,0.0000295206,0.000337911,0.00002719276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[8.723416e-7,0.00001387767,0.000008457662,0.0002851085,0.00001613479,0.000001952155,0.001567907,0.00002935857,5.488696e-8,0.0000281682,0.9770458,0.02100227],"study_design_scores_gemma":[0.0007424288,0.0002023758,0.02979835,0.008222891,0.0003812231,0.00005553359,0.006685498,0.1667311,0.000001025761,0.01466153,0.7720529,0.0004651399],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007395755,0.001042542,0.000002322956,0.0001647516,0.000003926263,0.0004360988,0.9972451,0.00001622317,0.0003494841],"genre_scores_gemma":[0.01759002,0.00007788825,0.00213733,0.0001981837,0.0001721275,0.002729296,0.9753056,0.000005218392,0.001784367],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6545717,"threshold_uncertainty_score":0.4521776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2273445524158683,"score_gpt":0.4993913389751332,"score_spread":0.272046786559265,"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."}}