{"id":"W3173319990","doi":"10.1609/aaai.v35i5.16512","title":"Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies","year":2021,"lang":"en","type":"article","venue":"","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":53,"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); Generalization; Branch and bound; Computer science; Tree (set theory); Benchmark (surveying); Search tree; Integer programming; Mathematical optimization; Theoretical computer science; Artificial intelligence; Mathematics; Search algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002851966,0.0001227512,0.0001722227,0.0001000809,0.0001051772,0.0002035298,0.00008120373,0.00005489449,0.0001198674],"category_scores_gemma":[0.0001617067,0.0001306346,0.00003605181,0.0003720181,0.00002077074,0.0001258193,0.00008303435,0.0001576207,0.00003426239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000328445,"about_ca_system_score_gemma":0.00001765665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005296962,"about_ca_topic_score_gemma":0.00005201079,"domain_scores_codex":[0.9991086,0.00008667794,0.0001772199,0.0001887842,0.0001411007,0.0002976604],"domain_scores_gemma":[0.9994439,0.0001863185,0.000007953611,0.0001968716,0.00004447281,0.0001204984],"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":[0.000003726113,0.00001082485,0.006459753,0.00007599044,0.00004865971,0.000007993401,0.002694035,0.7342113,0.1725713,0.00114716,0.0001976918,0.0825715],"study_design_scores_gemma":[0.0007702989,0.00006345731,0.06400644,0.000160297,0.00003336949,0.0001144033,0.001300989,0.6107487,0.312485,0.0004963033,0.008828674,0.0009920463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6990386,0.0001815836,0.2929699,0.0004776995,0.0001143507,0.00006029387,0.000001723806,0.0003779286,0.006778036],"genre_scores_gemma":[0.832525,0.00004579211,0.1659568,0.0003349617,0.00007646538,0.000004675275,0.000002611642,0.00004074236,0.00101293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1399137,"threshold_uncertainty_score":0.5327125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03093705308793026,"score_gpt":0.3004092617432398,"score_spread":0.2694722086553095,"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."}}