{"id":"W7116666449","doi":"10.1007/978-3-032-13509-4_25","title":"LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Benchmark (surveying); Generalization; Key (lock); Code (set theory); Language model; Computational linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.001049081,0.0006976873,0.0007149564,0.0004331112,0.000465501,0.0003058743,0.001509229,0.001482479,0.000161534],"category_scores_gemma":[0.0002776793,0.0007623902,0.0003779345,0.0004544341,0.0001461768,0.0001703927,0.000401266,0.002438193,0.00001990576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006046259,"about_ca_system_score_gemma":0.0006279156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002900476,"about_ca_topic_score_gemma":0.0002853618,"domain_scores_codex":[0.9961609,0.0002581056,0.0007096277,0.001323645,0.0009276713,0.0006200818],"domain_scores_gemma":[0.9968072,0.001139893,0.0004941192,0.001030629,0.0004217982,0.0001064045],"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":[0.00001649237,0.0000306269,0.00005052226,0.00002213901,0.00003604235,0.000004465981,0.0003500625,0.6182975,0.000001396553,0.06819507,0.000247545,0.3127481],"study_design_scores_gemma":[0.0006094183,0.00002491049,0.0002232587,0.00020878,0.00006217372,8.252338e-7,5.754179e-7,0.7949375,0.000002200609,0.2012216,0.0021871,0.0005216622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00002420846,0.001193955,0.8682988,0.001619922,0.0006245733,0.001238176,0.00001528013,0.0002854819,0.1266996],"genre_scores_gemma":[0.9225202,0.00004391517,0.07135838,0.001549397,0.002224362,0.0002554547,0.0003897513,0.0001045002,0.001554105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9224959,"threshold_uncertainty_score":0.9998632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01698227311453109,"score_gpt":0.3057661589263878,"score_spread":0.2887838858118567,"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."}}