{"id":"W4401418492","doi":"10.2139/ssrn.4919717","title":"Detection of Counterfeit Coins Using Multimodal Gpt-4 and Vision Transformer","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Currency Recognition and Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Counterfeit; Transformer; Artificial intelligence; Computer vision; Computer science; Engineering; Electrical engineering; History; Voltage","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":[0.0004097803,0.000762413,0.0007773741,0.002005768,0.0002707893,0.0007919797,0.0006497834,0.001051644,0.004060585],"category_scores_gemma":[0.0009397057,0.0002189315,0.0006698808,0.001030921,0.000242648,0.0006566287,0.0009236641,0.0005679544,0.002340012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002426193,"about_ca_system_score_gemma":0.0004056003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001387211,"about_ca_topic_score_gemma":0.001700302,"domain_scores_codex":[0.9996821,0.00004367878,0.00001187144,0.00007095069,0.00009748196,0.00009396732],"domain_scores_gemma":[0.9997459,0.00004358761,0.00003229899,0.00004237342,0.0001003058,0.00003545973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001091366,0.000252888,0.01261319,0.0002667776,0.0001293708,0.000968046,0.00009618972,0.00899192,0.286314,0.00163213,0.006117889,0.6815262],"study_design_scores_gemma":[0.0000620921,0.000584603,0.04462419,0.00007182087,0.0002264216,0.003182356,0.0002280069,0.733862,0.2077437,0.003793962,0.005537048,0.00008369185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5543661,0.001388379,0.4228677,0.0004869596,0.0002311725,0.0002712057,0.0014377,0.005715076,0.01323581],"genre_scores_gemma":[0.8927231,0.0004186092,0.1014766,0.0001349846,0.00007113737,0.000065554,0.0008423621,0.0001004977,0.004167327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004060585,"threshold_uncertainty_score":0.01358408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01429022857617651,"score_gpt":0.2915104288816124,"score_spread":0.2772202003054359,"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."}}