{"id":"W4380632342","doi":"10.1002/aaai.12095","title":"Evaluation and Design of Generalist Systems (EDGeS)","year":2023,"lang":"en","type":"article","venue":"AI Magazine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Scalability; Theme (computing); Machine learning; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001883556,0.0000804154,0.0001233355,0.0001409609,0.00006266792,0.00009346247,0.0003041231,0.00003719966,0.00001212392],"category_scores_gemma":[0.0001910728,0.00007620847,0.00001784758,0.0006830686,0.00005806841,0.0003565507,0.000129583,0.00004736802,0.0003845085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003044713,"about_ca_system_score_gemma":0.00007006995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005096586,"about_ca_topic_score_gemma":0.000008324359,"domain_scores_codex":[0.9987354,0.0001925925,0.0002245185,0.0002439435,0.0004150481,0.0001885527],"domain_scores_gemma":[0.9990379,0.0001146751,0.00007086003,0.000367914,0.0003581557,0.00005046171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002063728,0.0001124211,0.0007869846,0.0001754537,0.00008212212,0.00006327089,0.002778907,0.2100663,0.1694756,0.3085382,0.09459902,0.2133011],"study_design_scores_gemma":[0.00008673593,0.0000813136,0.0007845182,0.00002019632,0.00001168322,0.000007312576,0.0000291448,0.9751069,0.01438207,0.007168772,0.002224795,0.00009654873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01944891,0.00061326,0.9758244,0.001589933,0.0005760749,0.0005154932,0.000002141321,0.0002038631,0.001225883],"genre_scores_gemma":[0.9942242,0.00008095192,0.004318541,0.00015248,0.000079371,0.00005548767,0.000004624413,0.00001024749,0.001074121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9747753,"threshold_uncertainty_score":0.4942207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09645042184813814,"score_gpt":0.3236505820579593,"score_spread":0.2272001602098211,"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."}}