{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002831714,0.00006542866,0.00006657072,0.00002854301,0.0001180868,0.0000187341,0.0003910448,0.00003835849,0.00002453239],"category_scores_gemma":[0.00001497463,0.00003743222,0.00002453875,0.0001632982,0.00002234905,0.0001717141,0.00008486342,0.00008470583,0.00001791981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006154817,"about_ca_system_score_gemma":0.00001982872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000247072,"about_ca_topic_score_gemma":0.000002459362,"domain_scores_codex":[0.9994006,0.00005149713,0.0001345988,0.0001361937,0.0001382347,0.0001388713],"domain_scores_gemma":[0.9994593,0.00006720747,0.00007373427,0.0003250472,0.00004384086,0.00003090548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001081511,0.0003011782,0.4415135,0.0001064677,0.000102233,0.00004378899,0.0435776,0.001481146,0.02803288,0.06764818,0.006049021,0.4110358],"study_design_scores_gemma":[0.000537143,0.0003513767,0.06813382,0.0005557081,0.00002601851,0.00003337472,0.0004111313,0.1691294,0.7484467,0.00848981,0.003378567,0.0005069561],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03909259,0.0001306076,0.9521249,0.0002163718,0.0004454743,0.00006389396,4.622073e-7,0.0001164175,0.007809313],"genre_scores_gemma":[0.9598196,0.000006346463,0.03983621,0.00003168299,0.00004506165,0.000004164584,4.267506e-7,0.000003076956,0.0002534843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.920727,"threshold_uncertainty_score":0.1526441,"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."}}