{"id":"W4409365321","doi":"10.1609/aaai.v39i11.33208","title":"Learning Valid Dual Bounds in Constraint Programming: Boosted Lagrangian Decomposition with Self-Supervised Learning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Dual (grammatical number); Decomposition; Lagrangian; Constraint (computer-aided design); Computer science; Mathematical optimization; Constraint programming; Artificial intelligence; Mathematics; Applied mathematics; Stochastic programming; Chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0005371284,0.0002235293,0.0002563036,0.0003309881,0.0003169272,0.0004606364,0.0005837693,0.0001052656,0.00003619137],"category_scores_gemma":[0.0002094463,0.0001818401,0.00007799173,0.001323143,0.0002304367,0.0004394652,0.000157579,0.0005557456,0.00001235632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001031942,"about_ca_system_score_gemma":0.0002207502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004508686,"about_ca_topic_score_gemma":0.0000499744,"domain_scores_codex":[0.9982514,0.00005768362,0.0005128973,0.0004768579,0.0003631294,0.0003380463],"domain_scores_gemma":[0.998858,0.0001095856,0.0002845409,0.0001503542,0.0005309268,0.00006664559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000132399,0.0002446971,0.01382832,0.00008759195,0.00004195204,0.000002803478,0.004660676,0.003722571,0.01269241,0.5950762,0.00001017041,0.3695002],"study_design_scores_gemma":[0.0003581934,0.0008647639,0.004285985,0.00122539,0.00004921257,0.00003345654,0.006011173,0.8163868,0.1559592,0.01382248,0.0003819833,0.0006214183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6866004,0.00002239446,0.277038,0.007037104,0.0004450498,0.001413011,0.000001600296,0.0006699761,0.0267725],"genre_scores_gemma":[0.9838174,0.00001799665,0.01585957,0.0001051401,0.00001484419,0.00003445227,0.00000181187,0.000009111612,0.0001396739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8126642,"threshold_uncertainty_score":0.7415223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02759433636576968,"score_gpt":0.2845751334361449,"score_spread":0.2569807970703752,"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."}}