{"id":"W4402670184","doi":"10.18653/v1/2024.findings-acl.627","title":"LLM Performance Predictors are good initializers for Architecture Search","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Architecture; Computer science; Computer architecture","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.00248434,0.001599848,0.001003956,0.002810491,0.0008934678,0.001772509,0.001503357,0.001337665,0.0094592],"category_scores_gemma":[0.02387775,0.000841936,0.0006458272,0.001478607,0.0004798911,0.00355948,0.001393153,0.002919584,0.00744599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001135753,"about_ca_system_score_gemma":0.001578711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002081508,"about_ca_topic_score_gemma":0.004736814,"domain_scores_codex":[0.9981955,0.000713837,0.0001183656,0.000293565,0.0004678655,0.0002108029],"domain_scores_gemma":[0.9927912,0.003490579,0.0004346609,0.001372004,0.001640728,0.0002708111],"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":[0.001199943,0.000467094,0.02794594,0.000368396,0.0001390073,0.0001392982,0.0001871268,0.1212299,0.008819235,0.00995682,0.05106863,0.7784786],"study_design_scores_gemma":[0.0001018782,0.0003874208,0.003396418,0.0001601675,0.00008496962,0.00009551003,0.0001109591,0.9468549,0.01839817,0.02040637,0.009951791,0.00005138444],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1546296,0.002576638,0.7669942,0.002234611,0.0006217266,0.0003879188,0.002998742,0.04810709,0.02144951],"genre_scores_gemma":[0.6475566,0.0004353996,0.3327845,0.0006538084,0.0002870598,0.0005964329,0.004713325,0.002933581,0.01003928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0094592,"threshold_uncertainty_score":0.03164417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02301374538322617,"score_gpt":0.2768504187826188,"score_spread":0.2538366733993926,"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."}}