{"id":"W2966373041","doi":"10.1609/aaai.v33i01.33019751","title":"Model AI Assignments 2019","year":2019,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Variety (cybernetics); Dissemination; Computer science; Artificial intelligence; Core (optical fiber); Multimedia; World Wide Web; Telecommunications","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001936463,0.0001011033,0.0001040574,0.00006650908,0.00005324363,0.0001595936,0.0009408122,0.00004866849,0.0002812417],"category_scores_gemma":[0.00001216219,0.00008852407,0.0000449553,0.0002199764,0.00001528811,0.001022402,0.0002816736,0.00009731609,0.008074986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004763687,"about_ca_system_score_gemma":0.00006737517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006181394,"about_ca_topic_score_gemma":0.000005863937,"domain_scores_codex":[0.9988481,0.00002199156,0.0001675159,0.0003531018,0.0002893166,0.0003199129],"domain_scores_gemma":[0.9990644,0.0000349149,0.00003499404,0.0007142159,0.00006598558,0.00008549593],"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":[0.00000334407,0.00008314811,0.001143886,0.000005447706,0.00001008819,0.000005498826,0.0003700994,0.03660873,0.01565574,0.908315,0.02690556,0.01089346],"study_design_scores_gemma":[0.00004807821,0.00003808748,0.00005617151,0.00000428431,8.444371e-7,0.000001630884,0.00002256339,0.9177208,0.04571578,0.03389364,0.002363005,0.0001351515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01731926,0.00001589975,0.8998076,0.00148844,0.0003315455,0.0001626294,5.388313e-7,0.0001868449,0.08068718],"genre_scores_gemma":[0.9130118,0.000004537455,0.03494077,0.002926541,0.00001979237,0.000006644789,7.815868e-7,0.000008179993,0.04908099],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8956925,"threshold_uncertainty_score":0.9926974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02565795576023379,"score_gpt":0.2770858829021328,"score_spread":0.251427927141899,"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."}}