{"id":"W3046018217","doi":"10.48550/arxiv.2007.14461","title":"Modeling Behaviour to Predict User State: Self-Reports as Ground Truth","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Ground truth; State (computer science); Common ground; Computer science; Psychology; Artificial intelligence; Social psychology; Algorithm","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":[0.003464454,0.0008210459,0.00063572,0.001077713,0.000234283,0.001802076,0.0007292677,0.001068159,0.002017383],"category_scores_gemma":[0.01889123,0.0003941972,0.000557807,0.0009137091,0.0004929657,0.002211946,0.0007787629,0.00122113,0.001661328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003597589,"about_ca_system_score_gemma":0.0004303556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003021084,"about_ca_topic_score_gemma":0.002660381,"domain_scores_codex":[0.9977021,0.001301305,0.0001115112,0.0004979896,0.0003032767,0.00008375476],"domain_scores_gemma":[0.9862922,0.008215542,0.001308475,0.002683975,0.001238296,0.000261424],"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":[0.001074526,0.001553374,0.2320319,0.000828588,0.0009124008,0.000173233,0.003052362,0.08304346,0.02090313,0.01519755,0.01272159,0.628508],"study_design_scores_gemma":[0.0000559441,0.0005831221,0.1258826,0.0002179246,0.0002165573,0.0002117692,0.0007620335,0.8190832,0.01281783,0.03274083,0.007283759,0.0001444547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.245422,0.001017309,0.7354851,0.001307133,0.0002024654,0.0002229397,0.002708931,0.004359026,0.009275133],"genre_scores_gemma":[0.914939,0.0003211102,0.08084697,0.0002137762,0.00006226661,0.000143906,0.00188725,0.0001729434,0.001412755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003464454,"threshold_uncertainty_score":0.01832205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09784721173930638,"score_gpt":0.2384778792356532,"score_spread":0.1406306674963468,"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."}}