{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01373156,0.001372406,0.001356612,0.002290498,0.000775244,0.003027353,0.006779697,0.003016861,0.003748082],"category_scores_gemma":[0.08273254,0.001273507,0.002760796,0.00126978,0.00484894,0.006546552,0.0059543,0.004738107,0.0008625243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001939941,"about_ca_system_score_gemma":0.003789176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01592064,"about_ca_topic_score_gemma":0.01401965,"domain_scores_codex":[0.987911,0.00614549,0.0009534042,0.001578128,0.002702189,0.0007097942],"domain_scores_gemma":[0.9540765,0.0319724,0.002306484,0.006431702,0.003872389,0.001340505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006055828,0.0007969147,0.009317645,0.0004901552,0.0005401925,0.0006727274,0.0008395363,0.4634292,0.00531466,0.3118731,0.004288911,0.2018314],"study_design_scores_gemma":[0.00003830796,0.0001088341,0.0003897884,0.00005966687,0.00004290244,0.0000646051,0.00007686957,0.8435277,0.002121913,0.1518337,0.001714628,0.00002105686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003304288,0.000104433,0.9940006,0.0001920843,0.00002515649,0.0000927895,0.00009520578,0.001316811,0.00086863],"genre_scores_gemma":[0.1961902,0.0001335628,0.8007975,0.0002246935,0.00005953024,0.0004228658,0.0006637991,0.0003090791,0.001198773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01592064,"threshold_uncertainty_score":0.07262033,"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."}}