{"id":"W2397669334","doi":"","title":"The Fault, Dear Researchers, is not in Cranfield, But in our Metrics, that they are Unrealistic.","year":2012,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ranking (information retrieval); Measure (data warehouse); Test (biology); Data science; Information retrieval; Data mining","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":[0.002444066,0.0001068318,0.0001272449,0.0003100423,0.000149609,0.0002918897,0.001033959,0.00009112677,0.00002984186],"category_scores_gemma":[0.0005114346,0.00006536869,0.00004881862,0.0008576634,0.00002703102,0.0008881393,0.0003387973,0.0004049071,0.0002086471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000102669,"about_ca_system_score_gemma":0.00007352465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002879383,"about_ca_topic_score_gemma":0.0007807693,"domain_scores_codex":[0.9979874,0.0001776217,0.0002646028,0.0001559346,0.0007611309,0.0006532895],"domain_scores_gemma":[0.9988258,0.0003694721,0.00005986483,0.0004611161,0.0001197851,0.0001639234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001450289,0.0004476446,0.6085812,0.00006126437,0.00002364621,0.00006695477,0.0164379,0.00005088021,0.000169739,0.1757266,0.02676429,0.1715249],"study_design_scores_gemma":[0.00184912,0.0001428387,0.8800841,0.00005775103,0.000005621537,0.00001956549,0.01331651,0.0385771,0.01326312,0.002226002,0.04977476,0.0006834958],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.723383,0.001305191,0.1020377,0.09642253,0.002172168,0.002855372,0.00008570388,0.0004770989,0.07126124],"genre_scores_gemma":[0.9941494,0.0001239817,0.001295821,0.000995906,0.000037167,0.00001748824,0.000001497851,0.0000047177,0.00337402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2715029,"threshold_uncertainty_score":0.4352784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1519798433484288,"score_gpt":0.3618475906571991,"score_spread":0.2098677473087703,"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."}}