{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01545664,0.0009633404,0.0006222436,0.0009889671,0.0005329924,0.002800886,0.002536,0.00148584,0.005963166],"category_scores_gemma":[0.04096434,0.0005709861,0.0007582027,0.00054927,0.002666185,0.003604218,0.003002114,0.001388701,0.001010749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002557747,"about_ca_system_score_gemma":0.002228815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001547333,"about_ca_topic_score_gemma":0.001816743,"domain_scores_codex":[0.9803509,0.01210056,0.0008125204,0.002084095,0.00378425,0.0008676323],"domain_scores_gemma":[0.9756644,0.01234223,0.001416762,0.005700619,0.004273634,0.0006024539],"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":[0.002108495,0.0006270484,0.008580973,0.002712714,0.0003406163,0.0003562622,0.002047853,0.2257719,0.02256029,0.3093681,0.009008748,0.416517],"study_design_scores_gemma":[0.0006891341,0.003190992,0.002521944,0.000703933,0.000338381,0.0003192589,0.001020258,0.6619809,0.04451121,0.2241194,0.06050796,0.00009672827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1695168,0.001884464,0.7811029,0.001782842,0.0002972133,0.001591139,0.0004547057,0.005075191,0.0382948],"genre_scores_gemma":[0.6301828,0.0005025675,0.3623755,0.0005773224,0.00004324331,0.0006567462,0.0004642558,0.0006024499,0.004595038],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01545664,"threshold_uncertainty_score":0.08174354,"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."}}