{"id":"W3006406045","doi":"10.1609/aaai.v35i5.16512","title":"Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Institut de Valorisation des Données; Compute Canada; Canadian Institute for Advanced Research","keywords":"Branching (polymer chemistry); Branch and bound; Generalization; Computer science; Tree (set theory); Benchmark (surveying); Search tree; Integer programming; Mathematical optimization; Theoretical computer science; Artificial intelligence; Search algorithm; Mathematics; Algorithm; Combinatorics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009793458,0.0003854021,0.0004983865,0.0002906524,0.0003642433,0.002109713,0.002869545,0.0002085562,0.00002401521],"category_scores_gemma":[0.001043583,0.0003188359,0.0001595795,0.0006479735,0.0002514572,0.0003994556,0.003259223,0.001200722,0.0000366491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006378072,"about_ca_system_score_gemma":0.000226128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006800983,"about_ca_topic_score_gemma":0.00009902393,"domain_scores_codex":[0.9969807,0.00008043748,0.0006768173,0.001088487,0.0007092045,0.0004643568],"domain_scores_gemma":[0.9978465,0.0001974957,0.0004286264,0.000737285,0.0006187272,0.0001713078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004729295,0.0001033094,0.001313692,0.0003101681,0.00004690956,8.36729e-7,0.01278091,0.0009581202,0.1281509,0.4856405,0.00006086058,0.3705865],"study_design_scores_gemma":[0.00006533174,0.0004218067,0.01418275,0.003457573,0.00006385997,0.00002578026,0.003424157,0.2424575,0.6094867,0.124441,0.0005636814,0.001409834],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8833695,0.0001167878,0.09436721,0.01694307,0.0006657866,0.0005915137,0.00001324639,0.0001836727,0.003749183],"genre_scores_gemma":[0.990966,0.000137972,0.008030923,0.0004094997,0.0001243279,0.00004094474,0.000004666215,0.00002289258,0.0002628285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4813358,"threshold_uncertainty_score":0.9999264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1157952399877882,"score_gpt":0.3423432507773105,"score_spread":0.2265480107895222,"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."}}