{"id":"W4399261743","doi":"10.1609/socs.v17i1.31549","title":"Neural Sequence Generation with Constraints via Beam Search with Cuts: A Case Study on VRP","year":2024,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Combinatorial Search","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Sequence (biology); Vehicle routing problem; Computer science; Beam search; Mathematical optimization; Mathematics; Algorithm; Search algorithm; Biology; Routing (electronic design automation); Genetics; Computer network","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":[0.0006751022,0.0002038531,0.0001567609,0.0002297874,0.0002359895,0.0007027381,0.00112494,0.00005876621,0.000009254935],"category_scores_gemma":[0.00002758459,0.0001305524,0.00006317125,0.0006562654,0.0001810851,0.0006517833,0.0002795508,0.0005098734,0.000009308196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002973457,"about_ca_system_score_gemma":0.0001378924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004193538,"about_ca_topic_score_gemma":0.000008054132,"domain_scores_codex":[0.9974208,0.00003339133,0.0002512663,0.0005569965,0.001484008,0.0002535596],"domain_scores_gemma":[0.998705,0.0001051956,0.00007427233,0.0002112912,0.0008285219,0.00007576917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001552988,0.003461323,0.005092089,0.000258269,0.0009231752,0.002998753,0.01366559,0.00084172,0.7523086,0.1732803,0.001843878,0.04377336],"study_design_scores_gemma":[0.0009560909,0.004713382,0.00009270433,0.0001966924,0.00002017132,0.002663464,0.0005081134,0.02958602,0.9601147,0.0007641828,0.0001184244,0.0002660662],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886566,0.000005637105,0.002819865,0.002393781,0.001603566,0.000884964,0.000006621763,0.0002575261,0.003371453],"genre_scores_gemma":[0.9989443,0.000002614203,0.0003380435,0.0001136748,0.0003522838,0.00007843199,0.000001048547,0.00002188053,0.0001476893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2078061,"threshold_uncertainty_score":0.6776519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02698770765650642,"score_gpt":0.2916023087667478,"score_spread":0.2646146011102414,"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."}}