{"id":"W6891661904","doi":"10.4230/lipics.cp.2024.30","title":"Learning Precedences for Scheduling Problems with Graph Neural Networks","year":2024,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Resource-Constrained Project Scheduling","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; European Commission; Institut de Valorisation des Données; Polytechnique Montréal","keywords":"Leverage (statistics); Scheduling (production processes); Artificial neural network; Graph; Job shop scheduling; Dynamic priority scheduling","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005699729,0.0005569701,0.0006420019,0.001296701,0.0007379698,0.00283207,0.001404583,0.000385651,0.00006884055],"category_scores_gemma":[0.002365106,0.0004090274,0.000418939,0.002902989,0.0003196453,0.001079979,0.0002552392,0.001223255,0.00001992377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001877063,"about_ca_system_score_gemma":0.0003480725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006567493,"about_ca_topic_score_gemma":0.00108573,"domain_scores_codex":[0.994445,0.0003915804,0.001123974,0.001359848,0.001374178,0.001305404],"domain_scores_gemma":[0.9950651,0.002848008,0.0003893514,0.0008779113,0.000401238,0.0004183699],"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":[0.0001555721,0.0000477794,0.03249319,0.00006155387,0.00009279295,0.00005090713,0.000998573,0.8441467,0.00105218,0.006519567,0.0004691249,0.113912],"study_design_scores_gemma":[0.0003536057,0.0005506293,0.001380442,0.0002604127,0.00005502237,0.0002640157,0.001123294,0.9845581,0.0007884394,0.00739922,0.002713653,0.0005531495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1893711,0.003482785,0.8005256,0.002765898,0.0003033331,0.001531333,0.00001551647,0.001345216,0.0006591688],"genre_scores_gemma":[0.8706636,0.00008199659,0.1261495,0.0004054289,0.000391702,0.001025427,0.00001705323,0.0001135529,0.001151792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6812924,"threshold_uncertainty_score":0.9998361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03480361908635707,"score_gpt":0.3029718832723857,"score_spread":0.2681682641860287,"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."}}