{"id":"W2948323804","doi":"10.5281/zenodo.3241945","title":"Models and Data for Simple Applications of BERT for Ad Hoc Document Retrieval","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Simple (philosophy); Computer science; Information retrieval; Post hoc; Medicine","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001308754,0.000173203,0.0002503505,0.00009275553,0.00007004638,0.0002283308,0.003486849,0.0001001123,0.001040686],"category_scores_gemma":[0.0001384372,0.0001669864,0.00004971875,0.0001449114,0.000005507055,0.0008982971,0.002977448,0.00007314979,0.00008925044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001450889,"about_ca_system_score_gemma":0.00006799745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003666995,"about_ca_topic_score_gemma":0.000007623693,"domain_scores_codex":[0.9986248,0.000008604488,0.0002394585,0.0007069074,0.000211255,0.0002089465],"domain_scores_gemma":[0.9966494,0.0002259575,0.0002366994,0.002725068,0.0001101824,0.00005270338],"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":[0.000005357929,0.00001832491,6.629127e-9,0.001007126,0.00002929063,1.881045e-7,0.000002959918,0.000006190151,1.110877e-7,0.00008346279,0.9883209,0.01052606],"study_design_scores_gemma":[0.0003010766,0.00006763591,4.985524e-7,0.0001949635,0.00003209642,4.344475e-7,0.000002344173,0.031633,0.000004918175,0.001572509,0.9660038,0.0001867119],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[9.875351e-9,0.0005602798,0.034052,0.00008403543,0.0000540186,0.002103287,0.9631124,0.00002056176,0.00001347599],"genre_scores_gemma":[3.307206e-7,0.00008286047,0.01145614,0.0001099477,0.00009583476,0.0006413991,0.9873267,0.00001063259,0.0002761046],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03162681,"threshold_uncertainty_score":0.9998725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1144167700426753,"score_gpt":0.3490369527446988,"score_spread":0.2346201827020235,"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."}}