{"id":"W4384636956","doi":"10.1145/3539618.3591887","title":"MMEAD: MS MARCO Entity Annotations and Disambiguations","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Global Water Futures; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Computer science; Python (programming language); Information retrieval; Resource (disambiguation); Named entity; Precision and recall; World Wide Web; Database; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001136706,0.00003665491,0.00003814301,0.00006913509,0.0001163048,0.0001037754,0.0001734879,0.00001500417,0.00002889729],"category_scores_gemma":[0.00003656436,0.00003425889,0.00001347572,0.0003322334,0.00001460699,0.0002852692,0.0001520294,0.00003389028,0.0001464257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007243608,"about_ca_system_score_gemma":0.00001707883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001085391,"about_ca_topic_score_gemma":0.0001073338,"domain_scores_codex":[0.9995323,0.00001406683,0.00007965815,0.0001641503,0.0001017099,0.0001080631],"domain_scores_gemma":[0.9996408,0.00005047798,0.00001208284,0.0002305617,0.00002546085,0.00004061285],"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":[2.393891e-7,0.00002094964,0.006453479,0.000008695754,0.000007900278,0.000004195572,0.001307704,0.0008871498,0.0004227721,0.9206469,0.006616644,0.06362339],"study_design_scores_gemma":[0.000125629,0.000008617228,0.07670654,0.000004264174,0.000002585873,0.000002877723,0.00006792759,0.8697867,0.0001123617,0.04880825,0.00427216,0.0001020784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07946246,0.00001069538,0.9073217,0.005201837,0.0001601478,0.00005787587,0.000001530642,0.0003265746,0.007457181],"genre_scores_gemma":[0.9339074,0.00001275608,0.06105272,0.0002676213,0.00003499361,0.0000137526,0.000004435531,0.000003062759,0.004703202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8718386,"threshold_uncertainty_score":0.1882056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04196631591292097,"score_gpt":0.2830238869274379,"score_spread":0.2410575710145169,"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."}}