{"id":"W3157599687","doi":"","title":"DC3: A learning method for optimization with hard constraints","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Constraint (computer-aided design); Differentiable function; Grid; Mathematical optimization; Optimization problem; Deep learning; ENCODE; Constrained optimization; Algorithm; Artificial intelligence; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002762033,0.0002565852,0.0002951476,0.000223509,0.0002249444,0.0002975095,0.0004941542,0.0002303154,0.0001425377],"category_scores_gemma":[0.00008002813,0.0002936436,0.000154965,0.0004903903,0.00009964307,0.0004397385,0.0004044117,0.0004209267,0.000006666694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001506726,"about_ca_system_score_gemma":0.0004077005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002966794,"about_ca_topic_score_gemma":0.00003116075,"domain_scores_codex":[0.9982855,0.0001991867,0.0001787936,0.0009936913,0.00008720896,0.0002556264],"domain_scores_gemma":[0.9984634,0.0001742968,0.0002837709,0.0005124583,0.0004376523,0.0001284074],"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":[0.00002020546,0.00002443418,0.0006739539,0.00004332566,0.00008180169,0.00004659985,0.0002093903,0.9668823,0.00001232855,0.02691845,0.00002451867,0.005062637],"study_design_scores_gemma":[0.000695696,0.00005455552,0.0002561269,0.00009428109,0.00007243761,0.00002029319,0.0002608485,0.9973544,0.00006631217,0.0006021805,0.0001701626,0.0003526374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00198681,0.00001259012,0.9951686,0.0001660213,0.000306832,0.0004335447,0.000008640619,0.0002991388,0.001617881],"genre_scores_gemma":[0.4307016,0.00005560274,0.5682597,0.0000849862,0.00002750569,0.000003166094,0.00008857794,0.00001614974,0.0007626759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4287148,"threshold_uncertainty_score":0.9999515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05739591779876293,"score_gpt":0.2025298560040661,"score_spread":0.1451339382053032,"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."}}