{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002589939,0.0003122719,0.0002969255,0.0001915944,0.000255743,0.0004888492,0.0007422382,0.0002698789,0.0002913652],"category_scores_gemma":[0.00006730981,0.0003996919,0.0002226353,0.000529269,0.0001378873,0.0005242471,0.001294646,0.0007423162,0.00003803349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002519655,"about_ca_system_score_gemma":0.0003838523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001371034,"about_ca_topic_score_gemma":0.00002668753,"domain_scores_codex":[0.9979839,0.0001619876,0.0002886131,0.001018304,0.0001486649,0.0003985646],"domain_scores_gemma":[0.9984661,0.00006168061,0.000318979,0.0006850262,0.0002690434,0.0001991681],"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":[0.000005488915,0.00004977623,0.00281274,0.00006897197,0.0001492861,0.0002028389,0.00057243,0.9509031,0.00009303042,0.03105664,0.0009752415,0.01311046],"study_design_scores_gemma":[0.0006275633,0.00003943803,0.000192489,0.0001283612,0.00005428392,0.00002041438,0.0004992151,0.9911109,0.0001329276,0.0003838995,0.006230309,0.0005801585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01820769,0.00003992737,0.9733552,0.000154232,0.0004255533,0.0003401843,0.000002298655,0.0004789643,0.006995963],"genre_scores_gemma":[0.9845372,0.000150564,0.01084221,0.0001485418,0.00003019757,0.000002053315,0.0001044943,0.00001733205,0.004167369],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9663296,"threshold_uncertainty_score":0.9998455,"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."}}