{"id":"W2757125855","doi":"10.1609/aiide.v13i1.12927","title":"Deep Learning for Real-Time Heuristic Search Algorithm Selection","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Classifier (UML); Incremental heuristic search; Machine learning; Portfolio; Beam search; Artificial intelligence; Heuristic; Algorithm; Search algorithm; Data mining","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003723747,0.0002979158,0.0003225776,0.0001361205,0.0008096836,0.001975755,0.001675847,0.00008570691,0.00003546263],"category_scores_gemma":[0.0008613027,0.0002347885,0.0001772672,0.0001292181,0.0004263335,0.001888096,0.0007068692,0.0003315275,0.00007203208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001243883,"about_ca_system_score_gemma":0.00004910786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007296681,"about_ca_topic_score_gemma":0.000005611668,"domain_scores_codex":[0.9978529,0.00001949961,0.0005544809,0.0006666552,0.000454436,0.0004519897],"domain_scores_gemma":[0.9979263,0.0002540703,0.0005568365,0.0003061352,0.0008309852,0.0001256611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002002682,0.0002856975,0.0007754362,0.00003702233,0.0000696046,8.089142e-7,0.002671084,0.0001456984,0.01615345,0.1431654,0.00004475222,0.8364508],"study_design_scores_gemma":[0.00003973642,0.0008722091,0.0003693777,0.0002435504,0.0000143627,0.000008084571,0.001595023,0.6284295,0.3252626,0.04271768,0.0001748453,0.0002729498],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2713584,0.00001947248,0.6950214,0.003684611,0.0008782455,0.001867664,0.00001967658,0.0001902051,0.02696029],"genre_scores_gemma":[0.9962777,0.00006598142,0.002325394,0.00005445113,0.00009356381,0.00007310442,0.000001862294,0.00001971855,0.001088248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8361778,"threshold_uncertainty_score":0.9990603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04766932784270206,"score_gpt":0.3175631529244489,"score_spread":0.2698938250817468,"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."}}