{"id":"W4398526658","doi":"10.7910/dvn/e4tlzv/fx9fz6","title":"AddFile1_SI.docx","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Programming language","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":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003124988,0.0005487613,0.0006962172,0.0003317797,0.0001473863,0.0007446512,0.00817242,0.0002882938,0.01813726],"category_scores_gemma":[0.0004010558,0.0005360023,0.00025798,0.0009351081,0.0000928252,0.001461505,0.004592696,0.0007349607,0.7432424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009473997,"about_ca_system_score_gemma":0.0003340938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002839105,"about_ca_topic_score_gemma":0.0001045249,"domain_scores_codex":[0.9962793,0.0001678184,0.0005582454,0.001475,0.0009470235,0.000572591],"domain_scores_gemma":[0.9931419,0.0001178947,0.0003972009,0.005797555,0.0000962331,0.0004492461],"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":[0.000006121675,0.00005346386,9.577013e-7,0.00006138437,0.0001399062,0.0005773913,0.00001368798,0.000003483858,0.000004625188,0.0003423647,0.9979784,0.0008181985],"study_design_scores_gemma":[0.0002615099,0.00005078223,0.000008192436,0.00004417263,0.0001701607,0.00002799638,0.000006606865,0.0008970803,0.00001613928,0.00006112931,0.9978719,0.0005843572],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[1.02097e-7,0.000001277558,0.01089364,0.00005484531,0.0009411538,0.0001994793,0.9873804,0.0002473989,0.0002816988],"genre_scores_gemma":[9.508709e-7,0.0002079217,0.008623229,0.002914674,0.0004243136,0.00002753937,0.987551,0.00002250496,0.000227806],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7251052,"threshold_uncertainty_score":0.9997091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01653565946018436,"score_gpt":0.2368974256858361,"score_spread":0.2203617662256517,"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."}}