{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008924486,0.0009961857,0.001119559,0.0060683,0.0009649474,0.002127939,0.002049365,0.001216838,0.8677206],"category_scores_gemma":[0.1304441,0.0005846688,0.001137856,0.00787686,0.0003715738,0.002807534,0.001331671,0.001155797,0.1456951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002000262,"about_ca_system_score_gemma":0.005099386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004391765,"about_ca_topic_score_gemma":0.00904374,"domain_scores_codex":[0.9966571,0.001302883,0.000784392,0.0004245026,0.0006791112,0.0001519944],"domain_scores_gemma":[0.8015961,0.1745834,0.005174018,0.003549573,0.01402026,0.001076673],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0003103027,0.000100166,0.001402239,0.009296212,0.00007044629,0.00006250285,0.0001938063,0.0005260039,0.00007237402,0.001254002,0.9613491,0.02536286],"study_design_scores_gemma":[0.003369259,0.0003262205,0.01598267,0.01241469,0.0005395541,0.0005616361,0.001370378,0.003013301,0.0009235322,0.0187036,0.9425899,0.0002052185],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0004408153,0.0000958032,0.001603326,0.0004038532,0.00005630014,0.0007276079,0.9938567,0.0005094326,0.002306066],"genre_scores_gemma":[0.02554623,0.0009673575,0.0422616,0.001698123,0.0003070946,0.02666706,0.8708453,0.002617524,0.02908971],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9910755,"threshold_uncertainty_score":0.1886804,"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."}}