{"id":"W4384811794","doi":"10.48550/arxiv.2307.09395","title":"Platelet Inventory Management with Approximate Dynamic Programming","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Blood donation and transfusion practices","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Markov decision process; Mathematical optimization; Leverage (statistics); Bellman equation; Computer science; Dynamic programming; Reinforcement learning; Stochastic programming; Operations research; Markov process; Mathematics; Artificial intelligence; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001533794,0.001213416,0.001695637,0.0006830674,0.0006012783,0.00235381,0.001416727,0.001694642,0.001833361],"category_scores_gemma":[0.005316569,0.0008693066,0.0007666182,0.0009654812,0.0009922567,0.001278885,0.001159083,0.001642844,0.0001855376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001904719,"about_ca_system_score_gemma":0.002485009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02198353,"about_ca_topic_score_gemma":0.009491929,"domain_scores_codex":[0.9992028,0.0002879162,0.00003768972,0.0001281116,0.0001930845,0.0001504245],"domain_scores_gemma":[0.9969454,0.002277417,0.0003147613,0.00007960721,0.0002643831,0.0001184259],"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":[0.00001343658,0.000007382784,0.0001053288,0.00000999696,0.000005882847,0.00001264467,0.000004994899,0.9970793,0.00004887988,0.001268032,0.00006913787,0.001374973],"study_design_scores_gemma":[0.000003657571,0.000006164495,0.00001786117,0.000001418419,0.000001671415,0.000002248742,0.000002057285,0.9987627,0.00002796394,0.001115636,0.00005742,0.000001199065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09659671,0.00129537,0.8924563,0.001029024,0.0001087021,0.0001174804,0.0002925598,0.0004319719,0.007671904],"genre_scores_gemma":[0.9437405,0.0004444209,0.05276201,0.0001546034,0.00004376737,0.0001412555,0.000215002,0.00004806594,0.002450373],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02198353,"threshold_uncertainty_score":0.04371113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06116335735055087,"score_gpt":0.1910246137971679,"score_spread":0.1298612564466171,"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."}}