{"id":"W4323356342","doi":"10.1162/qss_a_00250","title":"An open data set of scholars on Twitter","year":2023,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Dalhousie University","funders":"","keywords":"Social media; Altmetrics; Computer science; Data science; Event (particle physics); Set (abstract data type); Open data; Matching (statistics); Open science; World Wide Web; Data set; Information retrieval; Artificial intelligence","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","open_science","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","open_science"],"category_scores_codex":[0.08227329,0.0001442364,0.0004262713,0.04028047,0.0009421391,0.002773517,0.01877354,0.0000307043,0.00008738381],"category_scores_gemma":[0.1459059,0.00008769184,0.00003685646,0.2909728,0.002913368,0.005076125,0.01062496,0.0001926625,0.001171263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006291678,"about_ca_system_score_gemma":0.0004119649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000745255,"about_ca_topic_score_gemma":0.00002697435,"domain_scores_codex":[0.9861351,0.0003555812,0.0006196986,0.001525937,0.01069338,0.0006703112],"domain_scores_gemma":[0.9838663,0.006909742,0.00031817,0.002539584,0.006081601,0.0002846113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002556319,0.0006194036,0.2165436,0.00003443322,0.0001959283,0.00008084541,0.02163148,0.0007095907,0.06460918,0.1196824,0.3639739,0.2116636],"study_design_scores_gemma":[0.0008267585,0.003634661,0.7445951,0.00007432913,0.00001236518,0.000002107167,0.1113746,0.02692224,0.008792989,0.08088674,0.02233118,0.0005469031],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890797,0.0003393806,0.0002430249,0.002616073,0.0007257882,0.0003631132,0.0002542888,0.00003281769,0.006345853],"genre_scores_gemma":[0.9950615,0.0003163917,0.00349872,0.0001897618,0.00002569156,0.00001060621,0.000008415134,0.000007201482,0.0008816707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5280515,"threshold_uncertainty_score":0.9998001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9676859895836807,"score_gpt":0.7752727570725012,"score_spread":0.1924132325111795,"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."}}