{"id":"W4384524480","doi":"10.51964/hlcs15759","title":"Introduction: Content, Design and Structure of Major Databases with Historical Longitudinal Population Data","year":2023,"lang":"en","type":"article","venue":"Historical Life Course Studies","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Linkage (software); Data science; Crowdsourcing; Computer science; Database; Population; Information retrieval; World Wide Web; Sociology","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":[],"consensus_categories":[],"category_scores_codex":[0.001782785,0.0001874326,0.0005943865,0.0002239315,0.0002930169,0.00004383586,0.0006007276,0.00003580963,0.00006810984],"category_scores_gemma":[0.005555424,0.0001250426,0.00003340344,0.0009571941,0.0001791778,0.0006336502,0.0008680952,0.0001262135,0.00002586792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003646422,"about_ca_system_score_gemma":0.00004923312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004880358,"about_ca_topic_score_gemma":0.0003195168,"domain_scores_codex":[0.9966872,0.0002718964,0.0006640106,0.0008546551,0.001294173,0.0002280034],"domain_scores_gemma":[0.9968247,0.001047099,0.0003547987,0.001264462,0.0003777379,0.0001312442],"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":[0.0001789287,0.00007836526,0.01181292,0.00004262555,0.0001842015,0.00001623574,0.0002116104,0.00008602277,0.00002793112,0.005839248,0.9780908,0.003431077],"study_design_scores_gemma":[0.000748592,0.0003547891,0.07931451,0.00003423325,0.0004532344,0.00001176289,0.002404233,0.0004831942,0.00001306987,0.002381476,0.913439,0.0003618436],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.14309,0.102727,0.4197924,0.2916254,0.03204701,0.004724176,0.003966508,0.001482845,0.0005445943],"genre_scores_gemma":[0.9538645,0.001588194,0.02346593,0.0003794291,0.002884693,0.00003370182,0.0007274721,0.0000469806,0.01700907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8107745,"threshold_uncertainty_score":0.6650763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5645442949893535,"score_gpt":0.4397790172587845,"score_spread":0.124765277730569,"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."}}