{"id":"W3111850714","doi":"10.1109/syscon47679.2020.9275856","title":"Decision Tree-based Adaptive Approximate Accelerators for Enhanced Quality","year":2020,"lang":"en","type":"article","venue":"2020 IEEE International Systems Conference (SysCon)","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Overhead (engineering); Set (abstract data type); Tree (set theory); Computation; Decision tree; Quality (philosophy); Computer engineering; Algorithm; Data mining","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003627458,0.0003993766,0.0005437977,0.0001195283,0.00008677984,0.0002786047,0.0007682354,0.0001845808,0.0001745879],"category_scores_gemma":[0.0001443567,0.0003904243,0.0001710754,0.0002596129,0.00005297968,0.0005467794,0.00003761296,0.0002532478,0.0002924581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002577303,"about_ca_system_score_gemma":0.0001536286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004536006,"about_ca_topic_score_gemma":0.00003270243,"domain_scores_codex":[0.9974526,0.00007381573,0.0008716017,0.00055713,0.0006383621,0.0004065361],"domain_scores_gemma":[0.9984149,0.0003462731,0.0002138978,0.0002957422,0.000483854,0.0002453748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002453119,0.0002610361,0.001794209,0.00176199,0.001447772,0.00005152834,0.003686237,0.3763976,0.5165123,0.02722738,0.02711802,0.04128883],"study_design_scores_gemma":[0.001846949,0.0001769474,0.000349053,0.0002720805,0.00002453255,0.000001994719,0.0002590022,0.8929482,0.09882601,0.000115795,0.004601929,0.0005774715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1905738,0.00008639308,0.7994946,0.0002650803,0.004331651,0.00103902,0.0002561794,0.0005233958,0.003429885],"genre_scores_gemma":[0.9953605,0.00002270224,0.002942419,0.0001926859,0.0007296925,0.0004654943,0.00008138643,0.00007038629,0.0001347511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8047866,"threshold_uncertainty_score":0.9998547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06966126884295173,"score_gpt":0.2904625975016007,"score_spread":0.220801328658649,"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."}}