{"id":"W2902160170","doi":"","title":"Towards a Framework for Testing Learning from Observation of State-Based Agents.","year":2017,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; State (computer science); Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0007792095,0.0001514087,0.0001844587,0.0001061848,0.0006266583,0.0004491255,0.001044784,0.0001025383,0.00004271133],"category_scores_gemma":[0.006719028,0.0001564447,0.00006450871,0.0001641543,0.00009277654,0.000366685,0.00008272738,0.0002829296,0.00003110906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005720513,"about_ca_system_score_gemma":0.0005389636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003137008,"about_ca_topic_score_gemma":0.00002388033,"domain_scores_codex":[0.9982899,0.00007155541,0.0004167002,0.0004085074,0.0005853205,0.0002280366],"domain_scores_gemma":[0.9963388,0.001488268,0.0005640247,0.0003573498,0.001183168,0.00006834132],"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":[0.00005550354,0.00006698027,0.002520554,0.00001811399,0.00001332861,0.000001571613,0.0004539179,0.05238,0.001445059,0.6631516,0.00002926668,0.2798642],"study_design_scores_gemma":[0.00002421848,0.0001115551,0.004335203,0.0001620233,0.000002446895,8.906942e-8,0.00002089378,0.5587124,0.02333089,0.4131381,0.00005371094,0.0001085662],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02685131,0.000008859301,0.9696001,0.001752086,0.0002911655,0.0001881011,0.00003477372,0.00008112673,0.001192498],"genre_scores_gemma":[0.7580874,0.000001122404,0.2415585,0.0001954033,0.00006995526,0.00002502322,0.00002437979,0.000007100213,0.00003112048],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7312361,"threshold_uncertainty_score":0.8043789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3821023633065346,"score_gpt":0.3942640635304206,"score_spread":0.01216170022388596,"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."}}