{"id":"W4388117875","doi":"10.23919/eusipco58844.2023.10290040","title":"Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar","year":2023,"lang":"en","type":"article","venue":"","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Infineon Technologies (Canada)","funders":"","keywords":"Softmax function; Autoencoder; Computer science; Detector; Artificial intelligence; Radar; Range (aeronautics); Feature (linguistics); Benchmark (surveying); Feature learning; Deep learning; Object detection; Pattern recognition (psychology); Data mining; Telecommunications; Engineering","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":[0.00008888811,0.00005773013,0.00008458048,0.00003087698,0.00004498579,0.000006475793,0.00003655269,0.00004247735,0.00001548957],"category_scores_gemma":[0.00002798878,0.00005691565,0.00006503066,0.0002306396,0.00001574942,0.00003124983,0.000003268106,0.00003959359,0.00002746532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000020647,"about_ca_system_score_gemma":0.000004881373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006779945,"about_ca_topic_score_gemma":0.00001152023,"domain_scores_codex":[0.9996253,0.000007202015,0.0001272588,0.00008784419,0.00004785982,0.0001045585],"domain_scores_gemma":[0.9997026,0.0001111318,0.00001111151,0.0001081767,0.00003857442,0.00002845567],"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":[0.000008390817,0.0000193992,0.0001126168,0.000112087,0.00002355602,9.265085e-8,0.00001805848,0.003370697,0.3312475,0.002279344,0.0009399767,0.6618683],"study_design_scores_gemma":[0.0003605679,0.0000709589,0.01125025,0.00002017908,0.00004017391,6.414393e-7,0.00009267274,0.525705,0.4397141,0.008411375,0.01408398,0.0002500968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1786969,0.000004415429,0.819629,0.0000678369,0.0003792593,0.0002290715,0.00008498966,0.0004559377,0.0004525818],"genre_scores_gemma":[0.9760542,0.000004290509,0.02353955,0.000004779273,0.00009447727,0.000165573,0.00006662036,0.00001244393,0.00005808841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7973573,"threshold_uncertainty_score":0.2320953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0315686863825681,"score_gpt":0.2785362882618704,"score_spread":0.2469676018793023,"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."}}