{"id":"W4394446162","doi":"10.6084/m9.figshare.20402389.v1","title":"From Black Box to Shining Spotlight","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of British Columbia","funders":"","keywords":"Black box; Computer science; Artificial intelligence","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":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001344262,0.0002510384,0.0003722277,0.0001352887,0.00009539206,0.00009149709,0.0006761816,0.0001739946,0.9720435],"category_scores_gemma":[0.03174794,0.0002525094,0.00008260433,0.0001613524,0.000004790676,0.00002507193,0.0005135697,0.0004612785,0.009816145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009963015,"about_ca_system_score_gemma":0.000184736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000047867,"about_ca_topic_score_gemma":0.00002949453,"domain_scores_codex":[0.9985615,0.0001868265,0.0002926352,0.0003939389,0.0003260815,0.0002390194],"domain_scores_gemma":[0.994624,0.004166633,0.0002303045,0.0007811369,0.00007116987,0.0001268],"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":[0.0000052712,0.00003193737,5.827326e-8,0.0002407604,0.00003148149,0.00002557091,0.0004303668,0.000001149794,3.774886e-7,0.00002144286,0.999014,0.0001975508],"study_design_scores_gemma":[0.00006895302,0.0000222005,0.000007620125,0.0005200634,0.00004166183,0.000001776432,0.0004512898,9.379129e-7,0.00002236713,0.005354804,0.9932145,0.0002937652],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[9.650095e-7,0.00005354861,0.00001077049,0.0001389475,0.0009038838,0.0002880018,0.9980414,0.0001055278,0.0004569436],"genre_scores_gemma":[7.402694e-8,0.000005076305,0.01549835,0.0007516716,0.0005393176,0.0003958549,0.9811219,0.00004074224,0.001647034],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9622273,"threshold_uncertainty_score":0.9999927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3733571035956747,"score_gpt":0.4613425200466697,"score_spread":0.087985416450995,"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."}}