{"id":"W3014913653","doi":"10.17713/ajs.v49i2.907","title":"Fast Approximate Complete-data k-nearest-neighbor Estimation","year":2020,"lang":"en","type":"article","venue":"Austrian Journal of Statistics","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Nearest neighbor graph; k-nearest neighbors algorithm; Nearest-neighbor chain algorithm; Best bin first; Nearest neighbor search; Intrinsic dimension; Graph; Sorting; Data set; Set (abstract data type); Dimension (graph theory); Mathematics; Fixed-radius near neighbors; Nearest neighbour algorithm; Large margin nearest neighbor; Manifold (fluid mechanics); Algorithm; Computer science; Combinatorics; Data mining; Statistics; Artificial intelligence; Cluster analysis; Curse of dimensionality","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003989843,0.0001196821,0.0003173033,0.0001415441,0.00008606393,0.0002319409,0.002002894,0.00004178655,0.0001386376],"category_scores_gemma":[0.001648072,0.00009161911,0.00004700804,0.0009885879,0.00006679134,0.0006348512,0.000448063,0.0002447234,0.0000791204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001864914,"about_ca_system_score_gemma":0.00008365681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009030599,"about_ca_topic_score_gemma":0.000001480771,"domain_scores_codex":[0.9984133,0.00008746627,0.0005895517,0.0002345711,0.0004708346,0.0002043239],"domain_scores_gemma":[0.9981737,0.0003423481,0.0005218839,0.0004504095,0.0002188394,0.000292869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007208405,0.0002167205,0.001873051,0.00007223575,0.000348038,0.001033821,0.0004974827,0.008073506,0.0001129827,0.1223253,0.1437233,0.7216515],"study_design_scores_gemma":[0.0008843101,0.0006018901,0.00328294,0.00002040786,0.0001321964,0.00007556616,0.00008635376,0.9678012,0.00004510456,0.01036496,0.01646818,0.0002368553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000295867,0.00006296406,0.9937415,0.004680013,0.0001569286,0.00004701146,0.0009283667,0.00002205922,0.00006525229],"genre_scores_gemma":[0.2637072,0.00004575343,0.7354708,0.000456258,0.0001709863,3.32067e-7,0.0001184654,0.000005660219,0.00002449906],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9597277,"threshold_uncertainty_score":0.3736119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1114835536417602,"score_gpt":0.2919919520773583,"score_spread":0.1805083984355981,"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."}}