{"id":"W4295878695","doi":"10.1162/qss_a_00211","title":"Assessing the quality of bibliographic data sources for measuring international research collaboration","year":2022,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Data science; Quality (philosophy); Digital library; Data quality; Information retrieval; Conceptual framework; Metric (unit); Engineering","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","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.1379287,0.00007812503,0.0002221624,0.002603617,0.003779218,0.001015887,0.004895641,0.000007858378,0.00002896791],"category_scores_gemma":[0.05603263,0.00004930538,0.00004797191,0.01700875,0.003278573,0.003045732,0.004982365,0.0001482159,0.000005713658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007011552,"about_ca_system_score_gemma":0.0002695502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001001873,"about_ca_topic_score_gemma":0.0003252525,"domain_scores_codex":[0.9904249,0.001782903,0.0007391174,0.0007402979,0.006025782,0.0002870524],"domain_scores_gemma":[0.9756542,0.01611446,0.0007692903,0.001540132,0.005874872,0.0000469711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.000194262,0.0003303898,0.02050801,0.00006142253,0.0002954079,0.000001128038,0.04541436,0.002008259,0.009219865,0.8452355,0.05691098,0.01982039],"study_design_scores_gemma":[0.000219897,0.000163704,0.03754361,0.00001502422,0.000009911826,2.725601e-7,0.8053657,0.003295567,0.0006711425,0.1113956,0.04121264,0.0001069758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9379362,0.002868516,0.02290242,0.02746795,0.00257728,0.001202602,0.001079215,0.00003425503,0.003931494],"genre_scores_gemma":[0.9952641,0.0001267045,0.004207525,0.0001101265,0.00003150693,0.00009758058,0.00001564921,0.000003283281,0.0001435158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7599513,"threshold_uncertainty_score":0.9994339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9238412134420332,"score_gpt":0.7257074572657539,"score_spread":0.1981337561762793,"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."}}