{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008433986,0.001712606,0.001450475,0.003839014,0.00165469,0.005665061,0.002589151,0.003750791,0.002517392],"category_scores_gemma":[0.03638196,0.0007039399,0.001365191,0.005333798,0.01045589,0.01560955,0.006981918,0.007704989,0.0009619898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005111449,"about_ca_system_score_gemma":0.002120949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002113749,"about_ca_topic_score_gemma":0.0008348516,"domain_scores_codex":[0.9889525,0.00484448,0.0006750285,0.001451169,0.003586843,0.0004899949],"domain_scores_gemma":[0.9699526,0.02248113,0.001077649,0.003750214,0.002206883,0.0005315532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004387987,0.00001010014,0.0001398255,0.0001051553,0.00001287819,0.00003835374,0.0001871436,0.008526525,0.0003964227,0.9674222,0.001395693,0.02172165],"study_design_scores_gemma":[0.00001155094,0.0000463153,0.00008818461,0.00008675411,0.000009302898,0.00008824964,0.00005941759,0.03460187,0.0006433184,0.9543529,0.009983995,0.00002817246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007626212,0.01169998,0.9611024,0.004440162,0.0005378164,0.00007621528,0.0002857173,0.0001203847,0.01411116],"genre_scores_gemma":[0.3458187,0.02742319,0.6066864,0.003335783,0.003888643,0.0009937502,0.0009517718,0.0003322992,0.01056943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008433986,"threshold_uncertainty_score":0.04460371,"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."}}