{"id":"W2165122403","doi":"10.1007/s11192-006-0115-z","title":"Benchmarking scientific output in the social sciences and humanities: The limits of existing databases","year":2006,"lang":"en","type":"article","venue":"Scientometrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":506,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Benchmarking; Bibliometrics; Benchmark (surveying); Database; Bibliographic database; Computer science; Data science; Humanities; Library science; Geography; Management","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":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.2117948,0.001439185,0.006880512,0.03238686,0.003829374,0.04375171,0.01127166,0.004675381,0.003534663],"category_scores_gemma":[0.5079167,0.001413145,0.001819434,0.06568196,0.01033181,0.04727207,0.01580384,0.004585154,0.001405537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009074111,"about_ca_system_score_gemma":0.01632906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01179735,"about_ca_topic_score_gemma":0.01404912,"domain_scores_codex":[0.7648036,0.1055339,0.02635588,0.01334711,0.08669557,0.003263902],"domain_scores_gemma":[0.316423,0.5012513,0.0366108,0.06879453,0.06593689,0.01098346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006425818,0.000541784,0.07119978,0.008204056,0.002585909,0.0001567786,0.003876196,0.009439403,0.0008997864,0.2257134,0.02373902,0.6530012],"study_design_scores_gemma":[0.0002788573,0.000416201,0.05802187,0.01092755,0.001492411,0.0004308535,0.007455678,0.03048023,0.002502482,0.7635346,0.124113,0.0003461808],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2407868,0.2747482,0.1460774,0.1670558,0.003212487,0.0005292061,0.01471318,0.002469429,0.1504075],"genre_scores_gemma":[0.8173069,0.05303284,0.1107676,0.005823052,0.003822682,0.0006143718,0.005894138,0.0005688691,0.002169488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9676132,"threshold_uncertainty_score":0.9719973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8593883432201264,"score_gpt":0.609782680977184,"score_spread":0.2496056622429423,"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."}}