{"id":"W4362453037","doi":"10.1145/3590768","title":"MEDUSA: A Multi-Resolution Machine Learning Congestion Estimation Method for 2D and 3D Global Routing","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Design Automation of Electronic Systems","topic":"VLSI and Analog Circuit Testing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Tsing Hua University; Chinese University of Hong Kong; University of Hong Kong","keywords":"Computer science; Convolutional neural network; Router; Routing (electronic design automation); Network congestion; Real-time computing; Computer network; Artificial intelligence","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":[0.001908666,0.0001724163,0.000248768,0.0002501653,0.0004091478,0.0001142843,0.0002815464,0.0001154862,0.000001632756],"category_scores_gemma":[0.0004691544,0.000180098,0.00006636584,0.0008119101,0.00002137925,0.0004512457,0.000008683659,0.0001687065,0.00001161724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002622015,"about_ca_system_score_gemma":0.0001331295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001528782,"about_ca_topic_score_gemma":0.00001744742,"domain_scores_codex":[0.9980883,0.0004048518,0.0004671232,0.0003805267,0.0002693643,0.00038981],"domain_scores_gemma":[0.9982309,0.0009661904,0.0003154163,0.0002802337,0.0001494451,0.00005786937],"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":[0.000003196305,0.00003070405,0.00003992258,0.00007118803,0.00003552236,4.514505e-7,0.0002407476,0.7745385,0.001601749,0.004253915,0.000008233519,0.2191759],"study_design_scores_gemma":[0.0006831394,0.0003065136,0.0005223897,0.0001478531,0.00004072945,0.00004856769,0.00005754375,0.9964514,0.0006075921,0.0009500284,0.00002646542,0.0001577684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001054912,0.0002113425,0.9968375,0.0002385908,0.0001850842,0.0006861858,0.000008089737,0.0007652792,0.00001300443],"genre_scores_gemma":[0.8121279,0.00002236646,0.1875744,0.00001046269,0.00001797541,0.0001464239,0.00001871487,0.0000121358,0.00006965448],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8110729,"threshold_uncertainty_score":0.7344181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04535847245118739,"score_gpt":0.3110048256251456,"score_spread":0.2656463531739582,"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."}}