{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02885814,0.001777138,0.002216069,0.002937529,0.001831857,0.003304545,0.003640806,0.002348109,0.002784505],"category_scores_gemma":[0.0978837,0.001372437,0.003559507,0.004870268,0.00369891,0.00424699,0.004397699,0.005075898,0.0007369052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001831678,"about_ca_system_score_gemma":0.003014144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007120822,"about_ca_topic_score_gemma":0.006614512,"domain_scores_codex":[0.9773713,0.01757256,0.000707744,0.001883978,0.002039682,0.0004248247],"domain_scores_gemma":[0.917838,0.06654229,0.004334412,0.006746916,0.003870469,0.0006680093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002285455,0.0001563133,0.007161767,0.0007836375,0.0009542537,0.0003157507,0.001671955,0.1983832,0.0009501844,0.5622623,0.01067511,0.2164569],"study_design_scores_gemma":[0.00005518795,0.00007459627,0.0007317713,0.0001699419,0.00007109965,0.0001530756,0.0001722867,0.4653962,0.0005867753,0.5258775,0.006644804,0.0000667368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000985279,0.000221437,0.9979429,0.0003830211,0.00004682878,0.00003489304,0.00004594743,0.00006761678,0.0002720864],"genre_scores_gemma":[0.06728202,0.0008864866,0.9289562,0.0004250733,0.0003027242,0.0004504263,0.000445918,0.0000974919,0.001153718],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02885814,"threshold_uncertainty_score":0.1526182,"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."}}