{"id":"W4400005792","doi":"10.1007/s11750-024-00678-8","title":"Gaining insight into crew rostering instances through ML-based sequential assignment","year":2024,"lang":"en","type":"article","venue":"Top","topic":"Scheduling and Timetabling Solutions","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal; Group for Research in Decision Analysis","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Crew; Operations research; Mathematical optimization; Mathematics; Aeronautics; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001504662,0.0001497568,0.0002167025,0.0002148923,0.0003115879,0.0008775956,0.0004195769,0.00007583859,0.00076243],"category_scores_gemma":[0.0006883026,0.0001124163,0.0001390302,0.0009644449,0.0001028078,0.0004898134,0.0001092518,0.000207107,0.0009499796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009510283,"about_ca_system_score_gemma":0.0002336125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001111176,"about_ca_topic_score_gemma":0.00003509798,"domain_scores_codex":[0.9976119,0.000129409,0.0004643723,0.0005361158,0.0009471541,0.0003110397],"domain_scores_gemma":[0.99861,0.0006981019,0.00007246354,0.00043777,0.00009272099,0.00008891735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002125566,0.000424229,0.009015137,0.0002026151,0.000442146,0.000687589,0.05595665,0.1022284,0.04019071,0.140798,0.01892691,0.630915],"study_design_scores_gemma":[0.0005657276,0.0001504842,0.0008490472,0.0003992057,0.00006815762,0.00001614746,0.001250623,0.1084702,0.02026937,0.05696641,0.8104392,0.000555403],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3264486,0.007973621,0.5675785,0.006273282,0.005930064,0.0002580408,0.00001932452,0.0007877175,0.0847308],"genre_scores_gemma":[0.9846448,0.00001352753,0.01252788,0.0004200899,0.0003075609,0.00001752668,0.000004927283,0.00001631336,0.002047402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7915123,"threshold_uncertainty_score":0.9998279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2028994966871165,"score_gpt":0.4339951749443921,"score_spread":0.2310956782572756,"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."}}