{"id":"W7142399348","doi":"10.5281/zenodo.17981976","title":"Supplementary Material for Large Language Models for Metaheuristic Implementation: A Case Study with Variable Neighborhood Search","year":2025,"lang":"en","type":"dataset","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Scripting language; Variable (mathematics); Code (set theory); Metaheuristic; Key (lock); Upload; Variable neighborhood search; Language model","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":[0.001642584,0.004035863,0.001584831,0.003330426,0.001275492,0.002718528,0.004449968,0.004774721,0.1250798],"category_scores_gemma":[0.009702051,0.001149728,0.002574443,0.004937193,0.0006211184,0.0018497,0.001656526,0.002659654,0.1052851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002948894,"about_ca_system_score_gemma":0.003234046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06645506,"about_ca_topic_score_gemma":0.1611882,"domain_scores_codex":[0.9984038,0.0004429154,0.0001571366,0.000435613,0.0003144727,0.0002460669],"domain_scores_gemma":[0.9952919,0.002166929,0.0002029415,0.001085273,0.0009731296,0.0002797953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009423953,0.0001000452,0.0007300012,0.0005062874,0.00004361444,0.00003498861,0.00002020279,0.001915852,0.00009692392,0.0004300831,0.9918666,0.004161008],"study_design_scores_gemma":[0.001178011,0.0001170616,0.004895771,0.0005156383,0.0001304682,0.0002341754,0.0002922551,0.01376003,0.001341116,0.006229593,0.9711946,0.0001112309],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0005574689,0.0001079087,0.0003906995,0.0001372886,0.00005865562,0.00004208435,0.9966085,0.001168771,0.0009285642],"genre_scores_gemma":[0.001185736,0.00005896817,0.00170525,0.00008628723,0.00001003479,0.0002030795,0.9952708,0.0001771916,0.001302611],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1250798,"threshold_uncertainty_score":0.4184335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0153903162515803,"score_gpt":0.3071561247199779,"score_spread":0.2917658084683977,"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."}}