{"id":"W4226200202","doi":"10.1609/aaai.v36i4.20294","title":"Learning to Search in Local Branching","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Leverage (statistics); Local search (optimization); Mathematical optimization; Heuristic; Computer science; Linear programming; Mathematics; Integer programming; Algorithm; Constraint (computer-aided design); Local optimum; Artificial intelligence","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":[0.002624225,0.0008850309,0.001346564,0.0006109896,0.0004952814,0.000938496,0.00155097,0.001014236,0.00193949],"category_scores_gemma":[0.01226694,0.0006090765,0.0006484999,0.000524942,0.001755744,0.001679192,0.002175935,0.001662652,0.0003449194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009156871,"about_ca_system_score_gemma":0.001411619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002488571,"about_ca_topic_score_gemma":0.003000983,"domain_scores_codex":[0.9990926,0.0003682306,0.00004470332,0.0002180045,0.000170901,0.0001056434],"domain_scores_gemma":[0.9950988,0.003477889,0.000470869,0.0003861466,0.0003802368,0.0001862105],"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":[0.00007335099,0.00004862211,0.001255342,0.00006536147,0.00003236621,0.00005698385,0.00008674501,0.9464566,0.001158405,0.02658793,0.0006066845,0.02357178],"study_design_scores_gemma":[0.00001040494,0.00002624952,0.00004818724,0.00000702439,0.000004249913,0.000006911584,0.0000063349,0.9905098,0.0002118406,0.009004281,0.0001623235,0.000002318175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05914433,0.0003464857,0.9366181,0.0003046886,0.00002804165,0.0000618009,0.00003106007,0.000446032,0.003019456],"genre_scores_gemma":[0.8036363,0.0003237264,0.1925968,0.0003360815,0.0000585989,0.0002859716,0.0001510236,0.0001564128,0.002455104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002624225,"threshold_uncertainty_score":0.01387841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05860159410969267,"score_gpt":0.3077845184515558,"score_spread":0.2491829243418631,"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."}}