{"id":"W7106791967","doi":"10.48448/wv63-7304","title":"CEMTM: Contextual Embedding-based Multimodal Topic Modeling","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interpretability; Semantics (computer science); Consistency (knowledge bases); Topic model; Process (computing); Dependency (UML)","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":[],"consensus_categories":[],"category_scores_codex":[0.0008008464,0.0011102,0.0006935096,0.00120438,0.0003103269,0.001098169,0.00123065,0.0008784148,0.003777974],"category_scores_gemma":[0.003368916,0.0003302658,0.001104743,0.001315692,0.0003859611,0.002201027,0.001483838,0.001384235,0.00203706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006111303,"about_ca_system_score_gemma":0.0007119852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005014712,"about_ca_topic_score_gemma":0.006855345,"domain_scores_codex":[0.9995245,0.0001328304,0.00002652652,0.0001744234,0.00008688839,0.00005481644],"domain_scores_gemma":[0.9993894,0.0002797065,0.00005638122,0.0001078889,0.0001344944,0.0000320673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005015342,0.000187173,0.002535557,0.0006807438,0.0002645444,0.0003876095,0.0007072772,0.1276667,0.03236065,0.02164708,0.03112672,0.7819344],"study_design_scores_gemma":[0.00003061911,0.0001002175,0.0009726039,0.00006687702,0.00008361644,0.0002242,0.0001263709,0.9485238,0.009844906,0.02573726,0.01424417,0.00004523835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01560492,0.002066064,0.9731578,0.0003420119,0.0001345176,0.0001041977,0.001695435,0.00444408,0.002450943],"genre_scores_gemma":[0.4828392,0.002582323,0.4934284,0.0006581619,0.0005017309,0.0006174616,0.008660246,0.001198096,0.009514417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005014712,"threshold_uncertainty_score":0.01263863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05851600955201141,"score_gpt":0.3601128297324509,"score_spread":0.3015968201804395,"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."}}