{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0508668,0.001950275,0.001684479,0.003741745,0.001215666,0.01248333,0.004237613,0.002466185,0.02345571],"category_scores_gemma":[0.1089236,0.0009437636,0.001826592,0.004005316,0.004887272,0.01323138,0.0101257,0.004519078,0.01256321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001852378,"about_ca_system_score_gemma":0.004304034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001177613,"about_ca_topic_score_gemma":0.001388449,"domain_scores_codex":[0.9280351,0.04973821,0.004432627,0.005027679,0.01192528,0.0008410452],"domain_scores_gemma":[0.8720872,0.08383344,0.004902029,0.02213368,0.01393294,0.003110617],"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":[0.000898988,0.0003664488,0.002720732,0.003004029,0.0002189567,0.0001661353,0.002992777,0.004269614,0.003954761,0.205984,0.08298451,0.692439],"study_design_scores_gemma":[0.000304525,0.000605822,0.002169801,0.001970734,0.0001233224,0.0005462013,0.001032678,0.03508319,0.003874801,0.4389269,0.5151963,0.0001657905],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004099547,0.002462601,0.9274169,0.006320519,0.001127408,0.001001963,0.001239763,0.02049378,0.03583755],"genre_scores_gemma":[0.08137351,0.00272019,0.8832743,0.002615958,0.001192997,0.002288319,0.002890484,0.01127416,0.01237013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0508668,"threshold_uncertainty_score":0.2690126,"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."}}