{"id":"W3037129427","doi":"10.1609/aaai.v34i09.7072","title":"Model AI Assignments 2020","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"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":[0.00009227155,0.00009965081,0.0001000337,0.00001935133,0.00008071026,0.000167827,0.0009500681,0.000037294,0.0001455167],"category_scores_gemma":[0.00005236423,0.00009081956,0.00004409351,0.0003533655,0.0000212083,0.0007503602,0.0003361964,0.0001109013,0.001802596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002531317,"about_ca_system_score_gemma":0.0000629538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001725211,"about_ca_topic_score_gemma":0.00000459708,"domain_scores_codex":[0.9988952,0.00002367729,0.0001771165,0.000368304,0.0002693818,0.000266309],"domain_scores_gemma":[0.9993547,0.00002453737,0.00003025698,0.000327535,0.00005422429,0.0002087042],"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":[0.00001039446,0.0001019212,0.000511201,0.00001447517,0.00002187735,0.00007803401,0.003059295,0.05282323,0.01981107,0.7736431,0.1205534,0.02937192],"study_design_scores_gemma":[0.00003548215,0.00004448794,0.00001505859,0.000001774723,0.000001217713,0.000001109229,0.00004138356,0.9431054,0.0378408,0.01580609,0.002990836,0.0001163433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00135347,0.00001550905,0.9454004,0.02727828,0.00008717024,0.00009244429,6.036225e-7,0.0002808782,0.02549125],"genre_scores_gemma":[0.9114105,0.000005660269,0.06430666,0.02283945,0.00006302969,0.000008722655,5.753259e-7,0.00000765807,0.001357703],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9100571,"threshold_uncertainty_score":0.9989746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06656900982648457,"score_gpt":0.2883622453603586,"score_spread":0.2217932355338741,"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."}}