{"id":"W4412030662","doi":"10.1109/lcsys.2025.3586080","title":"All Data-Driven LQR Algorithms Require at Least as Much Interval Data as System Identification","year":2025,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Interval data; Identification (biology); Interval (graph theory); Algorithm; Computer science; System identification; Mathematics; Data mining","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001128637,0.0005129779,0.0008829791,0.0003330171,0.0002349433,0.0005413266,0.002375916,0.0002659728,0.00001577281],"category_scores_gemma":[0.00008970909,0.0005210104,0.0001429982,0.0003449458,0.00007137263,0.001068912,0.0002508434,0.0003604087,0.001542411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008546551,"about_ca_system_score_gemma":0.00005314342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001755958,"about_ca_topic_score_gemma":0.0002213279,"domain_scores_codex":[0.9958259,0.0004030773,0.001356474,0.001119435,0.0006317215,0.0006633454],"domain_scores_gemma":[0.9955198,0.0001771204,0.0002926731,0.003694294,0.0001118099,0.0002043569],"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":[0.0003470032,0.00008335216,0.000339584,0.003617308,0.004123236,0.0003416211,0.0005046764,0.1043771,0.5547338,0.0009511314,0.3242744,0.00630682],"study_design_scores_gemma":[0.00232834,0.00002170364,0.00007563583,0.0005487316,0.00022493,0.0001935946,0.0005651511,0.8556126,0.0002751276,0.000001580383,0.1397074,0.0004452678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2727246,0.008000209,0.5776987,0.01026605,0.09747891,0.00950738,0.004929231,0.008409423,0.01098551],"genre_scores_gemma":[0.994758,0.00001572541,0.00001582978,0.0008900574,0.001174168,0.0003029587,0.0005093308,0.00009489951,0.002239057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7512355,"threshold_uncertainty_score":0.9997241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02432628183153636,"score_gpt":0.2673919040864817,"score_spread":0.2430656222549453,"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."}}