{"id":"W2115215982","doi":"10.14778/1453856.1453883","title":"Hashed samples","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Similarity (geometry); Estimator; A priori and a posteriori; Computer science; Overhead (engineering); Set (abstract data type); Sampling (signal processing); Cosine similarity; Algorithm; Data mining; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","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":[0.001799994,0.0001101546,0.000216988,0.0001112632,0.0002291174,0.00008475884,0.001608782,0.00002763307,0.0002388175],"category_scores_gemma":[0.001475403,0.00006129144,0.0001436007,0.0005140385,0.0002042464,0.0003230026,0.0007911863,0.00007707236,0.0001401256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003216543,"about_ca_system_score_gemma":0.00002115617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008477276,"about_ca_topic_score_gemma":0.000006538192,"domain_scores_codex":[0.9974399,0.00001501746,0.0005259413,0.0003216953,0.001485928,0.0002115138],"domain_scores_gemma":[0.998863,0.0001727117,0.0003394307,0.0003123499,0.0002506686,0.00006179988],"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":[0.00008347817,0.0004162836,0.040989,0.0000521969,0.00009392198,0.000001707678,0.00402312,0.00002868511,0.01871645,0.2555075,0.6621273,0.01796035],"study_design_scores_gemma":[0.0008811202,0.0001198308,0.08030357,0.00004937867,0.00003711039,0.00002502613,0.003397773,0.00008660491,0.1193554,0.1306892,0.6647803,0.0002747251],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9066988,0.0001123909,0.0002972628,0.008024189,0.0005471967,0.0005888966,0.00003887616,0.00006138077,0.08363099],"genre_scores_gemma":[0.9917634,0.00004943211,0.001490486,0.0005860449,0.0000533831,0.00002270144,8.843631e-7,0.000006097551,0.006027601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1248183,"threshold_uncertainty_score":0.2989544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2910039101624485,"score_gpt":0.3717421828373335,"score_spread":0.08073827267488504,"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."}}