{"id":"W4414015757","doi":"10.11159/mvml25.113","title":"A Comparative Evaluation of Vision Language Models for Waste Classification in Few-Shot Settings","year":2025,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Municipal Solid Waste Management","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Shot (pellet); Computer science; Artificial intelligence; Natural language processing; One shot; Engineering; Materials science; Mechanical engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.003779049,0.002044901,0.001220124,0.001362894,0.0006583231,0.00186713,0.002370747,0.002289199,0.002464798],"category_scores_gemma":[0.01011646,0.0004171579,0.001176777,0.0008956557,0.000688279,0.003268861,0.001416361,0.002056468,0.00151549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001743756,"about_ca_system_score_gemma":0.001363395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01926858,"about_ca_topic_score_gemma":0.0211783,"domain_scores_codex":[0.9979451,0.0006500118,0.000132901,0.0006205864,0.0004137678,0.0002375769],"domain_scores_gemma":[0.9962972,0.002138316,0.0001721191,0.000440563,0.0007525958,0.0001992542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002594474,0.001779521,0.007267701,0.0009209262,0.0007069598,0.0003107335,0.0002895244,0.3698011,0.0166903,0.002849947,0.01052579,0.5862631],"study_design_scores_gemma":[0.00003014253,0.0003782256,0.001325986,0.00004037581,0.00005409469,0.00007665234,0.0001320153,0.9882642,0.007284932,0.001379199,0.0009909712,0.00004316022],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7131374,0.009481047,0.2402747,0.002093649,0.001148223,0.0004374032,0.002564622,0.0128415,0.01802136],"genre_scores_gemma":[0.8958076,0.001199856,0.09261559,0.0005369398,0.000136088,0.0001564263,0.004055372,0.0003733391,0.005118832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01926858,"threshold_uncertainty_score":0.03831285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02186614719294598,"score_gpt":0.2802667748184238,"score_spread":0.2584006276254778,"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."}}