{"id":"W4380995398","doi":"10.3390/app13127112","title":"Source Microphone Identification Using Swin Transformer","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Microphone; Computer science; Transformer; Digital audio; Identification (biology); Speech recognition; Audio analyzer; Artificial intelligence; Audio signal; Engineering; Telecommunications; Speech coding; Electrical engineering","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":[0.0006280824,0.0008673936,0.0008424701,0.0009704026,0.0003335054,0.001008943,0.001012792,0.0008870714,0.005938918],"category_scores_gemma":[0.001909194,0.0002965774,0.0007212191,0.000554496,0.0003504481,0.001272625,0.00162783,0.000815713,0.005064797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003204348,"about_ca_system_score_gemma":0.0006181635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001276129,"about_ca_topic_score_gemma":0.002038212,"domain_scores_codex":[0.999495,0.00007385503,0.00002674191,0.0001546379,0.0001961742,0.00005362159],"domain_scores_gemma":[0.9995876,0.00008238613,0.00004088282,0.00007997316,0.0001716361,0.00003757644],"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":[0.0008729094,0.0001409155,0.002174097,0.0002477796,0.000101812,0.0004880654,0.0001487228,0.0253404,0.1160399,0.003512207,0.007039787,0.8438933],"study_design_scores_gemma":[0.00006553421,0.0002508881,0.001727225,0.00004884973,0.0000869178,0.001768379,0.0001179889,0.8576849,0.1193162,0.004887812,0.01398094,0.00006446776],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01747767,0.0003118738,0.9729769,0.000133889,0.0001905628,0.00009947156,0.0002308085,0.005512044,0.003066826],"genre_scores_gemma":[0.5210111,0.0008532715,0.4627001,0.0004823895,0.0001631163,0.0001651864,0.001554092,0.000569582,0.01250125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005938918,"threshold_uncertainty_score":0.01986766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02935601443706471,"score_gpt":0.2557583507319746,"score_spread":0.2264023362949099,"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."}}