{"id":"W4403477213","doi":"10.1163/24523666-bja10046","title":"Educational and Career Trajectories in Russia: Introducing a New Source and Datasets with a High Granularity","year":2024,"lang":"en","type":"article","venue":"Research Data Journal for the Humanities and Social Sciences","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Granularity; Computer science; Political science; Mathematics education; Data science; Psychology; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.002159538,0.0004477905,0.0006838395,0.004862863,0.001088313,0.001989717,0.001266486,0.001728509,0.00406109],"category_scores_gemma":[0.01383379,0.0004302828,0.0014154,0.006776087,0.0005613249,0.001385946,0.003323267,0.001887062,0.003413836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001045184,"about_ca_system_score_gemma":0.001776299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01882433,"about_ca_topic_score_gemma":0.0273068,"domain_scores_codex":[0.9973961,0.0006858176,0.00041822,0.0007487864,0.0005023893,0.000248812],"domain_scores_gemma":[0.9940818,0.001711003,0.0006710117,0.002033127,0.001143218,0.0003599321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008904483,0.001080881,0.324115,0.002952997,0.0008632217,0.001037362,0.003851448,0.01580363,0.005103482,0.01684429,0.5011891,0.1262681],"study_design_scores_gemma":[0.0002045101,0.0001473489,0.3967539,0.000785596,0.00019386,0.0005128945,0.00290627,0.01153734,0.002750238,0.007675244,0.5763613,0.0001714492],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.07929819,0.0007370044,0.01217896,0.001857748,0.0005230432,0.0003668171,0.8985174,0.001433947,0.005086931],"genre_scores_gemma":[0.08577678,0.0003188112,0.03488856,0.0002456044,0.0001621608,0.001233095,0.8751268,0.0003131369,0.001935037],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01882433,"threshold_uncertainty_score":0.03742951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3758763393928578,"score_gpt":0.4910133060437998,"score_spread":0.115136966650942,"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."}}