{"id":"W2147607381","doi":"10.1177/1098214007309280","title":"The Evaluation of Large Research Initiatives","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Program evaluation; Agency (philosophy); Government (linguistics); Work (physics); Political science; Management science; Public relations; Public administration; Sociology; Engineering; Social science","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":["metaresearch"],"category_scores_codex":[0.3613473,0.001785546,0.002429208,0.02055239,0.005477903,0.01671479,0.003627355,0.002248733,0.00552063],"category_scores_gemma":[0.5048438,0.0007501174,0.00111175,0.02251466,0.005659251,0.01208037,0.01310085,0.002091287,0.001008721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02276064,"about_ca_system_score_gemma":0.03949312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005389399,"about_ca_topic_score_gemma":0.004339722,"domain_scores_codex":[0.4545095,0.4034488,0.02540201,0.01255778,0.09817842,0.005903495],"domain_scores_gemma":[0.2543141,0.5156031,0.04259395,0.04531682,0.1319751,0.010197],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002146187,0.002632642,0.06772961,0.00753504,0.00152378,0.0004025057,0.02768094,0.004817496,0.003534869,0.05350277,0.01617216,0.8123221],"study_design_scores_gemma":[0.00408297,0.02306516,0.3304878,0.01458847,0.003534067,0.0006938296,0.1513661,0.02874144,0.0262826,0.1216868,0.2944879,0.0009828226],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7063445,0.01478335,0.05792497,0.01953088,0.001384108,0.0283512,0.002609863,0.00178208,0.167289],"genre_scores_gemma":[0.900063,0.002928243,0.07829303,0.001400703,0.0005232908,0.01166955,0.001299659,0.0002109764,0.003611446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9794476,"threshold_uncertainty_score":0.7875726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8816684527440397,"score_gpt":0.727468180018336,"score_spread":0.1542002727257037,"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."}}