{"id":"W3210345906","doi":"10.32920/ryerson.14668203.v1","title":"Protected multimodal emotion recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Sadness; Computer science; Disgust; Feature (linguistics); Mel-frequency cepstrum; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Speech recognition; Emotion classification; Anger; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001745054,0.0002170856,0.0002114519,0.0001488822,0.00009278182,0.000512886,0.0004826908,0.0003874073,0.0004004123],"category_scores_gemma":[0.00008170396,0.0002047334,0.0001419356,0.0002045476,0.00001500244,0.0004537563,0.001066262,0.000546094,0.0003345188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005104341,"about_ca_system_score_gemma":0.0001441459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001472888,"about_ca_topic_score_gemma":0.00001586746,"domain_scores_codex":[0.9982918,0.0001602728,0.0002815028,0.0007366952,0.0003115723,0.0002181867],"domain_scores_gemma":[0.9987341,0.00002997428,0.0001528673,0.0006321067,0.0003633736,0.00008757652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000112894,0.0003095698,0.00003557773,0.0002294569,0.00005432805,0.00005105133,0.0009785958,0.0003136126,0.01581666,0.0001103634,0.003488532,0.978601],"study_design_scores_gemma":[0.001605969,0.0001651229,0.00488413,0.002625952,0.00004226193,0.00008343137,0.0004769491,0.6897752,0.2583933,0.03805739,0.001662081,0.002228202],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1212787,0.0000628061,0.870391,0.0008957309,0.001360521,0.0006141956,0.000009214054,0.0007366212,0.004651171],"genre_scores_gemma":[0.3892111,0.000150778,0.6077824,0.0006105676,0.0002542458,0.0003731248,0.0009355693,0.00002565783,0.0006565622],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9763728,"threshold_uncertainty_score":0.8348786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03400675894368906,"score_gpt":0.2550391256393022,"score_spread":0.2210323666956132,"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."}}