{"id":"W4416057143","doi":"10.48550/arxiv.2510.18803","title":"Decoding Funded Research: Comparative Analysis of Topic Models and Uncovering the Effect of Gender and Geographic Location","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Topic model; Latent Dirichlet allocation; Covariate; Probabilistic logic; Thematic map; Thematic structure; Function (biology); Statistical model","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007256541,0.0002603536,0.001099365,0.001147192,0.0007431393,0.00008694766,0.0004295317,0.0001998094,0.00003685087],"category_scores_gemma":[0.0003935717,0.0001990727,0.0003776997,0.004709304,0.001184317,0.0001725708,0.0007522313,0.0005213862,5.108732e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007278768,"about_ca_system_score_gemma":0.0001784216,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006775194,"about_ca_topic_score_gemma":0.002087124,"domain_scores_codex":[0.9938817,0.003594677,0.0007416622,0.0006822186,0.0007928398,0.0003069139],"domain_scores_gemma":[0.991352,0.006847325,0.0005140028,0.0004029357,0.0007886941,0.00009501714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006721703,0.00003407194,0.806511,0.0003651174,0.004278239,3.790224e-7,0.01968246,0.1558217,0.00008215999,0.006780121,0.000002003722,0.006375525],"study_design_scores_gemma":[0.0002600559,0.00008742126,0.7111844,0.0001710524,0.003233808,1.320681e-7,0.004789131,0.2627958,0.000377448,0.016892,0.00002596769,0.0001827252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725037,0.003378963,0.0207206,0.0001307725,0.0001100691,0.0005056449,0.00001229396,0.000008408706,0.002629579],"genre_scores_gemma":[0.9978471,0.00144223,0.000449114,0.00001225016,0.00005001996,0.00003414872,0.00001496747,0.000003971355,0.0001461927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1069741,"threshold_uncertainty_score":0.9998388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3391748008106125,"score_gpt":0.479066704623995,"score_spread":0.1398919038133825,"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."}}