{"id":"W2951446960","doi":"10.1145/3299869.3300094","title":"Fingerprints for Compressed Columnar Data Search","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Overhead (engineering); Block (permutation group theory); Data compression; Volume (thermodynamics); Compression (physics); Column (typography); Memory management; Compression ratio; Auxiliary memory; Data structure; Parallel computing; Minimax; Data compression ratio; Computer hardware; Semiconductor memory; Algorithm; Image compression; Artificial intelligence; Operating system; Computer network; Mathematics; Engineering","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":[0.0003453205,0.0000575732,0.00008082019,0.00004095093,0.00004692813,0.0002859112,0.003177473,0.00001538391,0.0001473071],"category_scores_gemma":[0.00001012687,0.00005203883,0.00001623515,0.0001292105,0.00001066504,0.0009946929,0.002347584,0.00003802481,0.0007478013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005947888,"about_ca_system_score_gemma":0.00001796101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003448827,"about_ca_topic_score_gemma":0.000005803404,"domain_scores_codex":[0.9991179,0.00001298702,0.00008900614,0.0004066808,0.0001732903,0.00020017],"domain_scores_gemma":[0.9981518,0.00007871477,0.00001729158,0.001682859,0.00003102883,0.00003835051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000149329,0.0002167562,0.002875891,0.0001515886,0.00008287095,0.000006915046,0.0001517086,0.0001468845,0.001163202,0.2942648,0.4126859,0.2882386],"study_design_scores_gemma":[0.0003472888,0.00003103626,0.0009542556,0.000005402686,0.00000177261,3.373814e-7,0.00001145531,0.7921508,0.0003238838,0.0004626548,0.2056171,0.00009400981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00179784,0.00001014584,0.9785023,0.001019299,0.0003757591,0.0004549652,0.00003897515,0.0001377629,0.01766296],"genre_scores_gemma":[0.2064086,0.00001650175,0.7284206,0.001539972,0.0001587139,0.00002658025,0.0004822547,0.00001891682,0.06292792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7920039,"threshold_uncertainty_score":0.9611723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08198813717934422,"score_gpt":0.3090936588729068,"score_spread":0.2271055216935626,"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."}}