{"id":"W4398289211","doi":"10.7910/dvn/eaxeet/o7vrne","title":"GoethePoetryReducedMinusLarge.zip","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001013773,0.003315611,0.001371992,0.004734946,0.001046221,0.003094006,0.003384478,0.002301116,0.086717],"category_scores_gemma":[0.005756201,0.0007732647,0.001313514,0.006455246,0.0006012583,0.001835171,0.002665434,0.001572986,0.1412215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001505527,"about_ca_system_score_gemma":0.002106853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01692783,"about_ca_topic_score_gemma":0.03287994,"domain_scores_codex":[0.9990632,0.0001520238,0.00009512601,0.0002979811,0.0002036707,0.0001879413],"domain_scores_gemma":[0.9980621,0.0004510958,0.000158593,0.0006459313,0.0004196423,0.0002626846],"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":[0.00003573714,0.00001745831,0.0003958886,0.0002535596,0.00001283521,0.00000962833,0.00001341048,0.0001214713,0.00006137613,0.0002607517,0.9970648,0.00175302],"study_design_scores_gemma":[0.0002874728,0.00002864185,0.002479056,0.0002170766,0.000028701,0.00006782569,0.00009997389,0.001014036,0.0006840043,0.001701715,0.9933621,0.00002949113],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002572165,0.00009404646,0.00009122591,0.00009921991,0.00004261465,0.00001493948,0.9971871,0.001173724,0.001039955],"genre_scores_gemma":[0.0006649811,0.00006954127,0.0003214749,0.00005296393,0.00001438822,0.00006018422,0.9978149,0.0001500279,0.0008514998],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.913283,"threshold_uncertainty_score":0.2900973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0322293650370897,"score_gpt":0.2631626910205373,"score_spread":0.2309333259834476,"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."}}