{"id":"W1823099761","doi":"10.5591/978-1-57735-516-8/ijcai11-330","title":"Monitoring the execution of partial-order plans via regression","year":2011,"lang":"en","type":"article","venue":"","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Robustness (evolution); Benchmark (surveying); Exploit; Regression; Plan (archaeology); Data mining; Mathematical optimization; Mathematics","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":[0.002236763,0.0008709009,0.0006719361,0.0008507684,0.0003813181,0.001025126,0.001130013,0.0005786606,0.001225141],"category_scores_gemma":[0.01541709,0.0005638768,0.0007011199,0.0006344168,0.001350726,0.002025482,0.001261517,0.001335614,0.0003133845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009020241,"about_ca_system_score_gemma":0.001449231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003547291,"about_ca_topic_score_gemma":0.003140354,"domain_scores_codex":[0.9970769,0.001017432,0.0001695012,0.0006016873,0.0009466335,0.0001879257],"domain_scores_gemma":[0.9898431,0.006538558,0.001533694,0.001320995,0.000624779,0.0001388209],"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":[0.0003187084,0.0001016097,0.003561762,0.0001828761,0.00007008798,0.0001584383,0.0002618838,0.7939147,0.02431828,0.02178086,0.0008601341,0.1544706],"study_design_scores_gemma":[0.00001424651,0.00006396857,0.00033963,0.000009985138,0.00001440972,0.00003658648,0.00002154929,0.9786516,0.01204334,0.007944998,0.0008481064,0.00001162368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03750382,0.00008127151,0.9583325,0.00009767585,0.000007366139,0.00008855807,0.00008679553,0.002910496,0.0008915706],"genre_scores_gemma":[0.5728857,0.0001221788,0.4255179,0.00004627456,0.00001458318,0.0001816577,0.0002497131,0.0002461082,0.0007358631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003547291,"threshold_uncertainty_score":0.01182932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04462964743055248,"score_gpt":0.250902412986188,"score_spread":0.2062727655556356,"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."}}