{"id":"W2599580500","doi":"10.1109/ita.2016.7888180","title":"On coding for data analytics: New information distances","year":2016,"lang":"en","type":"article","venue":"","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Coding (social sciences); Bounded function; Code word; Theoretical computer science; Computer science; Discrete mathematics; Analytics; Information theory; Algorithm; Combinatorics; Mathematics; Decoding methods; Data mining; 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":[0.00009589374,0.00004932747,0.00004502689,0.000009370865,0.00003393992,0.00001847186,0.0001849817,0.00004186272,0.00001610134],"category_scores_gemma":[0.000229761,0.00002495482,0.00002128419,0.00001859654,0.00001415479,0.000006637964,0.00009177162,0.00001024026,0.00001649525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000341867,"about_ca_system_score_gemma":0.00001595454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002899349,"about_ca_topic_score_gemma":0.000007408981,"domain_scores_codex":[0.9996448,0.00000556339,0.00009511131,0.0001222516,0.00003538564,0.00009688962],"domain_scores_gemma":[0.9996679,0.00003327672,0.00003487554,0.0002097171,0.00002143806,0.00003281646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003086005,0.00003175797,0.001955721,0.00001978683,0.00005819276,2.323043e-7,0.000009702201,0.00001488394,0.2283921,0.02682571,0.1580259,0.5843574],"study_design_scores_gemma":[0.001057826,0.0006788331,0.0006887842,0.00003401295,0.00001230678,0.000001243952,0.00003004029,0.001764325,0.09001306,0.003356247,0.9021109,0.0002524514],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0966874,0.00003885319,0.8957848,0.00090377,0.000138923,0.0001364167,0.00004759935,0.00003199547,0.006230233],"genre_scores_gemma":[0.9954379,0.00002541946,0.002674857,0.0005935028,0.0001675029,0.000001208491,0.0001457642,0.000002663188,0.0009512238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8987505,"threshold_uncertainty_score":0.1017628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05599704649347067,"score_gpt":0.2962050638777133,"score_spread":0.2402080173842427,"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."}}