{"id":"W4396852896","doi":"10.1109/lnet.2024.3400764","title":"Unlocking Reconfigurability for Deep Reinforcement Learning in SFC Provisioning","year":2024,"lang":"en","type":"article","venue":"IEEE Networking Letters","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ciena (Canada); University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Reconfigurability; Provisioning; Reinforcement learning; Computer science; Artificial intelligence; Computer network; Telecommunications","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":[],"consensus_categories":[],"category_scores_codex":[0.0003410178,0.0001573859,0.0001461651,0.0001319748,0.00008901928,0.0001653996,0.00009335372,0.00006623452,0.00001520499],"category_scores_gemma":[0.00001459832,0.0001635835,0.00005948618,0.0001880577,0.00001259912,0.0001579871,0.000009881377,0.0002903041,0.000004692912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001637184,"about_ca_system_score_gemma":0.0000101727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000105565,"about_ca_topic_score_gemma":0.00001341404,"domain_scores_codex":[0.9989792,0.00001683827,0.000289079,0.0002530839,0.0001085591,0.0003532742],"domain_scores_gemma":[0.9996685,0.0001525141,0.00002650655,0.0001065901,0.00001123415,0.0000346121],"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":[0.000005931055,0.00000133238,0.0002685173,0.0003396772,0.00001445584,0.000004325105,0.0004647207,0.9252817,0.0004928496,0.00001614132,0.0003355386,0.07277481],"study_design_scores_gemma":[0.0001417771,0.00001455823,0.00009565974,0.0004409176,0.000009211077,0.000001636237,0.00001427623,0.9799804,0.001988021,0.00005321866,0.01706409,0.0001962289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08724447,0.0007242012,0.9065009,0.0003430808,0.002940316,0.0004304274,2.525488e-7,0.0008693489,0.000947014],"genre_scores_gemma":[0.9976922,0.00006093948,0.001261306,0.000164737,0.0006258594,0.00008490748,0.00001227153,0.00005071668,0.00004709657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9104477,"threshold_uncertainty_score":0.667074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01182303755301757,"score_gpt":0.2193040530904228,"score_spread":0.2074810155374052,"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."}}