{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001753389,0.00008714107,0.00007459476,0.00008655828,0.0001244574,0.0003153621,0.0006114792,0.000035705,0.00001635564],"category_scores_gemma":[0.000009347926,0.0000678787,0.00004495052,0.0003601299,0.00003252603,0.0002825615,0.0001510874,0.0001183732,0.00006495243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001784252,"about_ca_system_score_gemma":0.00007530918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001057097,"about_ca_topic_score_gemma":0.000004640336,"domain_scores_codex":[0.9991592,0.000009555702,0.0001108513,0.000338105,0.0001609143,0.0002214098],"domain_scores_gemma":[0.9994087,0.00009970824,0.0000126688,0.0003682097,0.00003627827,0.00007440456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003017998,0.00006673847,0.000366103,0.0001812452,0.00004154665,0.000005185809,0.001125589,0.0003144397,0.0001031117,0.1275426,0.01886007,0.8513903],"study_design_scores_gemma":[0.0001514907,0.0001561377,0.001868487,0.00008142804,0.000008051892,0.00002262981,0.00007543811,0.7235043,0.001632964,0.001188275,0.271118,0.0001928341],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008335113,0.00009393822,0.9819408,0.002490024,0.0002941643,0.0002312883,0.00007681402,0.0004850277,0.006052817],"genre_scores_gemma":[0.6551461,0.00003882202,0.3391902,0.0004286761,0.0003792125,0.0002645176,0.00005986922,0.00002369262,0.004468903],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8511975,"threshold_uncertainty_score":0.3041044,"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."}}