{"id":"W4307136417","doi":"10.1177/00811750221125799","title":"Sparse Data Reconstruction, Missing Value and Multiple Imputation through Matrix Factorization","year":2022,"lang":"en","type":"article","venue":"Sociological Methodology","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Canadian Institutes of Health Research; Defense Advanced Research Projects Agency; National Center for Science and Engineering Statistics; National Science Foundation","keywords":"Imputation (statistics); Missing data; Categorical variable; Matrix decomposition; Computer science; Data mining; Sparse matrix; Probabilistic logic; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00314682,0.0001078037,0.0002746256,0.00004109279,0.002156118,0.00003133292,0.0002498929,0.0001638492,0.0003967605],"category_scores_gemma":[0.007370867,0.00009699512,0.00003901881,0.0002219108,0.0007248975,0.0002503733,0.000318859,0.0002672152,0.000004983317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001226,"about_ca_system_score_gemma":0.00009144223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007047397,"about_ca_topic_score_gemma":0.00004825191,"domain_scores_codex":[0.9932125,0.00559738,0.000278054,0.0004435131,0.0001990353,0.0002695002],"domain_scores_gemma":[0.9945012,0.004993738,0.000194626,0.0001769071,0.00007768307,0.00005584322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002187599,0.0001704051,0.3157094,0.00002956005,0.0002536805,0.00001266819,0.12889,0.001051454,0.002361763,0.4025415,0.004418822,0.144342],"study_design_scores_gemma":[0.0009439141,0.0002591524,0.03225113,0.000005119625,0.00009810762,0.00003327677,0.08628532,0.003356758,0.00004948493,0.8030254,0.07324571,0.0004465855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3054547,0.002818227,0.6693676,0.01286506,0.00355693,0.0007291636,0.0001694146,0.0003966025,0.004642307],"genre_scores_gemma":[0.8567322,0.0004931235,0.1414181,0.0005086637,0.0004534678,0.00002069508,0.0001139732,0.000009046137,0.0002506901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5512776,"threshold_uncertainty_score":0.9991429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4555094762158756,"score_gpt":0.4649924861828348,"score_spread":0.009483009966959222,"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."}}