{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008323546,0.001220983,0.0007602075,0.001336969,0.0003197351,0.001091306,0.001336347,0.0009217405,0.003460783],"category_scores_gemma":[0.003366289,0.0003526366,0.001221978,0.001473806,0.0003898756,0.002240883,0.001557635,0.00150703,0.001900414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006347268,"about_ca_system_score_gemma":0.0007030322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004740887,"about_ca_topic_score_gemma":0.006866054,"domain_scores_codex":[0.9995277,0.0001270581,0.00002785566,0.000175821,0.00008529378,0.00005621051],"domain_scores_gemma":[0.9993731,0.0002994819,0.0000565288,0.0001058835,0.0001315879,0.00003336068],"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":[0.0005194713,0.000185127,0.002567719,0.0007336339,0.000284978,0.0003603697,0.0007240897,0.1471994,0.03148256,0.02092239,0.02765536,0.7673648],"study_design_scores_gemma":[0.00003095455,0.0001007278,0.0008293895,0.00005850923,0.00008478114,0.0002149639,0.0001143785,0.9577773,0.008497976,0.02087406,0.01137625,0.00004070486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0134471,0.001786642,0.977178,0.0002747317,0.0001194421,0.0001073446,0.001563619,0.003824445,0.001698762],"genre_scores_gemma":[0.440617,0.002718492,0.5365986,0.0006049244,0.0005496495,0.0007802493,0.009240293,0.001149622,0.007741195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004740887,"threshold_uncertainty_score":0.01157749,"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."}}