{"id":"W4393764489","doi":"10.5281/zenodo.3269890","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":"Computer science; Simple (philosophy); Information retrieval","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":[],"consensus_categories":[],"category_scores_codex":[0.004109168,0.004079988,0.001386435,0.003584197,0.001400216,0.003205648,0.004608174,0.002780313,0.05968488],"category_scores_gemma":[0.01800391,0.001085042,0.002634014,0.003974863,0.0008179285,0.003127022,0.002255711,0.003260238,0.1163407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00232318,"about_ca_system_score_gemma":0.002805716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02385134,"about_ca_topic_score_gemma":0.05282189,"domain_scores_codex":[0.9974903,0.0005769058,0.000251252,0.0006750753,0.0006758557,0.0003305375],"domain_scores_gemma":[0.9940028,0.001393613,0.0001767183,0.002887699,0.001255031,0.0002843351],"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":[0.0002132765,0.0001567794,0.0009308092,0.0004257426,0.00007450107,0.00004064193,0.0000242935,0.005682025,0.0003659061,0.0009407126,0.9690676,0.02207769],"study_design_scores_gemma":[0.001256176,0.0004580541,0.008406469,0.000435757,0.0002120451,0.0005341158,0.0003456893,0.1543118,0.01177508,0.02248703,0.7995348,0.0002429241],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.009711821,0.00164687,0.01569847,0.001621794,0.002143593,0.0007464733,0.8947479,0.05856062,0.01512242],"genre_scores_gemma":[0.01491262,0.0003592466,0.01885037,0.0003340917,0.0001966451,0.0005265539,0.9550624,0.002040303,0.007717829],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05968488,"threshold_uncertainty_score":0.1996658,"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."}}