{"id":"W2923890923","doi":"10.48550/arxiv.1903.10972","title":"Models and Data for Simple Applications of BERT for Ad Hoc Document Retrieval","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Simple (philosophy); Sentence; Information retrieval; Microblogging; Inference; Question answering; Social media; Post hoc; Artificial intelligence; Natural language processing; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.0003158163,0.000158997,0.0002676929,0.0001145996,0.00007864724,0.00005446932,0.002249076,0.0001523998,0.000001917701],"category_scores_gemma":[0.00002206638,0.0001872908,0.00008465823,0.0001451529,0.0000404597,0.0004215115,0.003226808,0.000128231,0.000001605009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006717345,"about_ca_system_score_gemma":0.0001747021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003262486,"about_ca_topic_score_gemma":0.00001460079,"domain_scores_codex":[0.9984087,0.00002137722,0.0001951675,0.001106546,0.00006555331,0.0002026884],"domain_scores_gemma":[0.9968013,0.0001995964,0.000218781,0.002533732,0.0001712658,0.00007539152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009099273,0.00006616045,0.0001046316,0.0005930613,0.0001282449,0.00000150244,0.0002251632,0.4470136,0.0000380584,0.544091,0.0006268015,0.007020822],"study_design_scores_gemma":[0.0003905009,0.00003062299,0.000008129604,0.00002026747,0.00004906574,3.722496e-7,0.00002020169,0.7566535,0.00004412411,0.2386168,0.004020929,0.0001454112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01315847,0.0002021558,0.984423,0.0001134157,0.0001246346,0.001494524,0.0002965126,0.00005099668,0.0001362709],"genre_scores_gemma":[0.9300584,0.0002575517,0.06866575,0.00004074825,0.00004073524,0.000006647239,0.0001710582,0.00001310497,0.0007459943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9168999,"threshold_uncertainty_score":0.7637495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1510945483297511,"score_gpt":0.2488475987278627,"score_spread":0.09775305039811166,"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."}}