{"id":"W4287326329","doi":"10.48550/arxiv.2102.09193","title":"SeaPearl: A Constraint Programming Solver guided by Reinforcement\\n Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Solver; Heuristics; Computer science; Leverage (statistics); Constraint programming; Mathematical optimization; Theoretical computer science; Artificial intelligence; Mathematics; Programming language; Stochastic programming","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":[0.000929172,0.0009992141,0.0007219837,0.0004935302,0.0004435122,0.001323721,0.001990519,0.001477762,0.01053321],"category_scores_gemma":[0.004880236,0.0005494632,0.0007550263,0.0005852735,0.0009516077,0.001206045,0.001803705,0.002382508,0.001543736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008994152,"about_ca_system_score_gemma":0.003327189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007059928,"about_ca_topic_score_gemma":0.0135321,"domain_scores_codex":[0.9993953,0.0001674499,0.00003141639,0.0001219629,0.0001908353,0.00009300065],"domain_scores_gemma":[0.9986847,0.0008746989,0.00009758785,0.00009846314,0.0001642707,0.00008024939],"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":[0.000131967,0.0001493846,0.001043945,0.0002568145,0.000056315,0.000229547,0.000117716,0.7868383,0.002423208,0.05691134,0.01835952,0.1334819],"study_design_scores_gemma":[0.00003466153,0.00001751567,0.00002742915,0.00001147826,0.000003643247,0.00002226396,0.00001149783,0.9877685,0.0008334454,0.006720723,0.004543749,0.000005178098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009424573,0.0001833811,0.9732064,0.0004614933,0.0001040214,0.0001527701,0.0003712335,0.004699287,0.01139687],"genre_scores_gemma":[0.1395342,0.0002368704,0.8491223,0.0004770856,0.00005018902,0.0003718239,0.0007242157,0.001058527,0.008424697],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01053321,"threshold_uncertainty_score":0.03523713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05221672463766503,"score_gpt":0.1946177107221411,"score_spread":0.1424009860844761,"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."}}