{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics","sts"],"category_scores_codex":[0.1096677,0.0001949995,0.0003290084,0.09872509,0.003340084,0.008372738,0.005001927,0.00006397161,0.00005347781],"category_scores_gemma":[0.0424663,0.00009916171,0.0001264725,0.4899217,0.004215502,0.001024178,0.001090991,0.0003571564,0.00002100305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008810357,"about_ca_system_score_gemma":0.0003217917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006184105,"about_ca_topic_score_gemma":0.000325578,"domain_scores_codex":[0.9785785,0.0006287548,0.001089237,0.001084996,0.01760306,0.00101544],"domain_scores_gemma":[0.9792731,0.01692205,0.0006137859,0.0008311887,0.002273005,0.00008680503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001396402,0.0005389262,0.6458755,0.00003892137,0.000009499257,0.00002085178,0.005744464,0.0002930244,0.0008386985,0.1505293,0.04421008,0.1518868],"study_design_scores_gemma":[0.0005538083,0.0002009237,0.8460857,0.00003439848,0.00001493752,0.00002083643,0.01289672,0.008677776,0.0006360377,0.01239758,0.1181039,0.0003774033],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9622965,0.002488917,0.0007473676,0.0009150481,0.0009381889,0.0003670611,0.00007395211,0.00001454747,0.03215842],"genre_scores_gemma":[0.9974456,0.00004071513,0.000840781,0.000138778,0.0002049772,0.00001050257,0.000006302359,0.000006962935,0.001305384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3911966,"threshold_uncertainty_score":0.9984944,"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."}}