{"id":"W2895868736","doi":"10.3233/aic-170537","title":"Performance robustness of AI planners in the 2014 International Planning Competition","year":2018,"lang":"en","type":"article","venue":"AI Communications","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Agile software development; Solver; Computer science; Robustness (evolution); Software; Benchmark (surveying); Competition (biology); Homogeneous; Software engineering; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000425791,0.00005835419,0.00006817948,0.000108632,0.0001753554,0.00006130847,0.003502191,0.00003045865,0.0000207394],"category_scores_gemma":[0.00004509328,0.00004869464,0.00002261135,0.0002804358,0.0003110014,0.0004668516,0.0003992639,0.0002045716,0.00005271826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002468249,"about_ca_system_score_gemma":0.00004251748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006873473,"about_ca_topic_score_gemma":0.000126938,"domain_scores_codex":[0.9992489,0.0001216244,0.0002393031,0.0001087342,0.0001725864,0.0001088604],"domain_scores_gemma":[0.9982231,0.0002495713,0.00008762544,0.001249048,0.0001759311,0.0000146717],"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":[0.0000248599,0.0005037351,0.1158782,0.0000170219,0.0000412836,0.000001625422,0.03031843,0.03989365,0.0006069683,0.7613787,0.01687326,0.03446221],"study_design_scores_gemma":[0.00005635406,0.00005603005,0.02032983,0.00007769473,0.000002649994,0.000008715906,0.0005658553,0.961843,0.000976935,0.001890036,0.01409961,0.00009325703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2111345,0.0001759715,0.7025282,0.05481829,0.0008473094,0.0003111521,0.00000760298,0.0001115001,0.03006551],"genre_scores_gemma":[0.9882972,0.00004750728,0.01077001,0.0007691044,0.00005255256,0.00002198107,0.00001186595,0.000003122415,0.00002661641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9219494,"threshold_uncertainty_score":0.6508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06033374970487245,"score_gpt":0.3527300751938626,"score_spread":0.2923963254889901,"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."}}