{"id":"W3193692689","doi":"10.1145/3465373","title":"A Deep Learning Framework to Predict Routability for FPGA Circuit Placement","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Reconfigurable Technology and Systems","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Field-programmable gate array; Overfitting; Convolutional neural network; Deep learning; Process (computing); Computer engineering; Artificial intelligence; Placement; Netlist; Computer architecture; Artificial neural network; Parallel computing; Algorithm; Machine learning; Embedded system; Circuit design; Physical design","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002782542,0.0001978545,0.0003349264,0.0003216719,0.0002464387,0.00005485135,0.0001924637,0.0004878859,0.00009100441],"category_scores_gemma":[0.0001450829,0.0002116255,0.00006948486,0.0004824871,0.0000417741,0.00007105802,0.000003354042,0.0005297302,0.00001918685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009313539,"about_ca_system_score_gemma":0.00002038765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006939239,"about_ca_topic_score_gemma":0.00001359503,"domain_scores_codex":[0.9988341,0.00004348603,0.0003279961,0.0003640267,0.00009013661,0.0003402002],"domain_scores_gemma":[0.9989881,0.000263932,0.0000306495,0.0005429611,0.00008731862,0.00008706484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001167198,0.0003216176,0.001625835,0.001686478,0.0008822755,0.00004094341,0.001486349,0.1904138,0.03117341,0.01271474,0.000638243,0.7588996],"study_design_scores_gemma":[0.003013726,0.003362691,0.0005967937,0.002440828,0.000497814,0.0008874703,0.01420969,0.1384991,0.621602,0.07527906,0.1365202,0.003090548],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01771727,0.001350707,0.9764385,0.0003159761,0.0004531398,0.0007546244,0.00002486974,0.001744956,0.001199963],"genre_scores_gemma":[0.9940256,0.000234174,0.003965689,0.00003687085,0.0000282506,0.001115847,0.000006749908,0.00003685789,0.0005499386],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9763083,"threshold_uncertainty_score":0.8629839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01829405432440499,"score_gpt":0.2363576123645851,"score_spread":0.2180635580401801,"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."}}