{"id":"W4407398990","doi":"10.32388/39knz3","title":"Review of: \"Are Vision-Language Models Truly Understanding Multi-vision Sensor?\"","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Vision science; Computer science; Artificial intelligence; Computer vision; Cognitive science; Psychology","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"],"consensus_categories":[],"category_scores_codex":[0.001582904,0.0005978098,0.001889676,0.0003814807,0.0001203668,0.0001379652,0.001967557,0.0003708653,0.0001722251],"category_scores_gemma":[0.0004865115,0.000464361,0.0006536908,0.001120033,0.00005685713,0.0004374653,0.0008061217,0.0004633643,0.0001164982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003199736,"about_ca_system_score_gemma":0.0004809472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003737703,"about_ca_topic_score_gemma":0.0001039628,"domain_scores_codex":[0.9955786,0.0004109216,0.001335966,0.001133087,0.001028064,0.000513304],"domain_scores_gemma":[0.9958922,0.0003795424,0.000877604,0.002197483,0.0004375539,0.0002156441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000001931083,0.0000541932,3.847767e-7,0.0858523,0.00004321841,0.00003402375,0.00005456606,0.00001061837,0.000005666211,0.003157929,0.9015584,0.009226739],"study_design_scores_gemma":[0.0005699986,0.000105858,0.000001659839,0.5337265,0.0001629841,0.00003717475,0.00009708724,0.01672645,0.00002909159,0.0009240564,0.4467865,0.0008325688],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[8.822463e-8,0.477354,0.4753707,0.01142741,0.002651345,0.001096021,0.0001481599,0.0001944163,0.03175777],"genre_scores_gemma":[0.0001287449,0.65513,0.06356306,0.02678061,0.0004381665,0.00009612364,0.0007271401,0.00007836243,0.2530578],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4547719,"threshold_uncertainty_score":0.9997808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08651338753806165,"score_gpt":0.3575902725141161,"score_spread":0.2710768849760544,"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."}}