{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008062977,0.00006360289,0.000113042,0.0001705075,0.006718697,0.003126807,0.0004157998,0.00002706394,0.00004156346],"category_scores_gemma":[0.0004662719,0.00003815368,0.00001523883,0.0004025069,0.0024341,0.0008844784,0.0002042356,0.0002819802,2.3048e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004211637,"about_ca_system_score_gemma":0.000887796,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01751643,"about_ca_topic_score_gemma":0.03217027,"domain_scores_codex":[0.9983031,0.0003691423,0.0001265934,0.0002591427,0.0006593476,0.0002826783],"domain_scores_gemma":[0.9973941,0.002358785,0.0000295102,0.00006718077,0.000100848,0.00004956811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004483783,0.00002072129,0.002940849,0.00006165532,0.00008285529,0.000004873021,0.08862001,0.00001823359,0.000007426296,0.8093392,0.0151596,0.08369979],"study_design_scores_gemma":[0.0003235545,0.0001540094,0.01788541,0.0001141093,0.00007165024,0.0000373112,0.1234785,0.002439891,0.000001129146,0.2814215,0.5738783,0.0001945854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7410669,0.04721163,0.006831643,0.2010991,0.0009192908,0.0009371563,0.0008578993,0.00003682117,0.001039595],"genre_scores_gemma":[0.9895236,0.002499275,0.002449346,0.0001911633,0.003204016,0.00001307584,0.00008215281,0.000008601243,0.002028764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5587187,"threshold_uncertainty_score":0.9979081,"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."}}