{"id":"W3206483379","doi":"10.1145/3450337.3483495","title":"PathOS+: A New Realm in Expert Evaluation","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Usability; Interpretation (philosophy); Construct (python library); Field (mathematics); Realm; Data science; Human–computer interaction; Artificial intelligence; Expert system; Population","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":[0.0003632736,0.00005593035,0.00006973299,0.00004894524,0.00002221459,0.00008963559,0.0003036719,0.0000352253,0.0004287658],"category_scores_gemma":[0.0002521921,0.00005259347,0.00002558287,0.0004175871,0.00001019935,0.0003248082,0.0001313398,0.00005416315,0.000210324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006099058,"about_ca_system_score_gemma":0.0003262052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005403732,"about_ca_topic_score_gemma":0.0008240909,"domain_scores_codex":[0.9990282,0.00008925822,0.0001741587,0.0002695503,0.0002923451,0.0001464894],"domain_scores_gemma":[0.999355,0.00005420617,0.00002300229,0.000401566,0.0001127451,0.0000534467],"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":[0.000001152159,0.00004558256,0.000699563,8.710555e-7,0.000001815443,0.00003678925,0.004142823,0.0003090317,0.004171921,0.07491523,0.006107724,0.9095675],"study_design_scores_gemma":[0.0001088729,0.00002936347,0.00253011,0.0000279143,0.000001512399,0.0000173453,0.0006378273,0.7207248,0.1702912,0.09517796,0.01025375,0.0001993682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02991433,0.0006509803,0.9209111,0.006083726,0.0005598431,0.0001517667,1.056443e-7,0.0001263418,0.04160175],"genre_scores_gemma":[0.8008782,0.00007520395,0.1919457,0.002293016,0.0001619569,0.00002778014,0.000002114525,0.000007686515,0.00460832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9093682,"threshold_uncertainty_score":0.4694685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1039123918393606,"score_gpt":0.3703895560927099,"score_spread":0.2664771642533493,"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."}}