{"id":"W4416036370","doi":"10.18653/v1/2025.emnlp-main.590","title":"CEMTM: Contextual Embedding-based Multimodal Topic Modeling","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Topic model; Feature (linguistics); Field (mathematics); Key (lock); Context (archaeology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006433295,0.0005391287,0.0006126502,0.0004326637,0.000486771,0.0007876181,0.001951662,0.000353672,0.0003652076],"category_scores_gemma":[0.0001999372,0.0005551416,0.0003268546,0.0007265455,0.000102188,0.0006912357,0.0008157674,0.0006072261,0.0001399522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000244257,"about_ca_system_score_gemma":0.001038008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007859566,"about_ca_topic_score_gemma":0.000103181,"domain_scores_codex":[0.9955939,0.0001839946,0.001097526,0.001509697,0.0005891699,0.001025698],"domain_scores_gemma":[0.9972662,0.0002547229,0.0001331671,0.001719829,0.0003763631,0.0002497101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002387428,0.0001549254,0.0003711142,0.0001007426,0.00005664276,0.00001988449,0.0005277922,0.7956651,0.0001434497,0.08863032,0.0002835467,0.1140226],"study_design_scores_gemma":[0.001780596,0.00006795661,0.00002727705,0.0002870508,0.00004022368,0.000002295929,0.0001705893,0.9929205,0.0006711649,0.002668961,0.0008449735,0.0005183922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02884502,0.0007223188,0.9418374,0.004845614,0.00324599,0.000515993,0.000003451841,0.0003741017,0.01961016],"genre_scores_gemma":[0.8807309,0.00001201377,0.1078201,0.003588842,0.0002100949,0.00002566631,0.000002456685,0.00001837393,0.007591599],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8518858,"threshold_uncertainty_score":0.99969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03017076091419873,"score_gpt":0.2980552092464189,"score_spread":0.2678844483322201,"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."}}