{"id":"W6907304170","doi":"10.21227/ws3b-p740","title":"Test Set From 10.1016/j.specom.2019.06.002","year":2020,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Noise (video); Set (abstract data type); Test set; Data set; Background noise; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0006640559,0.001856221,0.002117266,0.0005070129,0.0002664679,0.0005313082,0.005377646,0.001237368,0.1360895],"category_scores_gemma":[0.001362375,0.001958734,0.0004502155,0.001008831,0.0003940906,0.0008463628,0.001401324,0.002762998,0.9530294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004380493,"about_ca_system_score_gemma":0.0009464697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004503674,"about_ca_topic_score_gemma":0.001530521,"domain_scores_codex":[0.9913267,0.000221199,0.001784414,0.003134778,0.002111151,0.001421756],"domain_scores_gemma":[0.9890826,0.0007074656,0.001548175,0.007348802,0.0002435629,0.00106937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008348717,0.0003974417,0.00004464457,0.0001359315,0.0004857802,0.002161556,0.00001960729,0.000002706375,0.0002562018,2.814285e-7,0.9963418,0.00007058875],"study_design_scores_gemma":[0.00108882,0.0001377772,0.0001641208,0.0002322201,0.00100262,0.00008578518,0.00002063089,0.00002220572,0.0002596985,0.00003579293,0.9948536,0.00209671],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001239513,0.0002072087,0.000006349302,0.0001389454,0.001049227,0.0009687058,0.9948955,0.0007296508,0.001991971],"genre_scores_gemma":[0.000002951559,0.0001119878,0.0003037593,0.0006717067,0.005232475,0.0001266027,0.9818929,0.0005713339,0.01108622],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8169399,"threshold_uncertainty_score":0.9995376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03911953994474811,"score_gpt":0.2763496036599193,"score_spread":0.2372300637151712,"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."}}