{"id":"W1506481577","doi":"","title":"Minimum description length principle: generators are preferable to closed patterns","year":2006,"lang":"en","type":"article","venue":"National University of Singapore","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Generator (circuit theory); Cardinality (data modeling); Computer science; Algorithm; Closed set; Minimum description length; Set (abstract data type); Equivalence class (music); Digital pattern generator; Mathematics; Data mining; Discrete mathematics; Power (physics)","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":[0.0001276482,0.00006890151,0.00008144188,0.0001224328,0.00019289,0.00004330811,0.0004259924,0.00004281314,0.00001765082],"category_scores_gemma":[0.0000136534,0.00008371494,0.00003258423,0.000289922,0.00002267565,0.0003732959,0.0001269615,0.00005790953,0.00001954416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059377,"about_ca_system_score_gemma":0.00008934271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001790824,"about_ca_topic_score_gemma":0.00009366084,"domain_scores_codex":[0.9992098,0.00001707689,0.0001004715,0.000240219,0.0003203598,0.0001121181],"domain_scores_gemma":[0.9993617,0.00002371925,0.000101051,0.0001769181,0.0002857921,0.0000508026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00006286735,0.002102961,0.06730192,0.000142969,0.0001517618,0.00006533862,0.003261312,0.01634229,0.03082442,0.6208389,0.170362,0.08854322],"study_design_scores_gemma":[0.00170998,0.0001682845,0.5806412,0.0001507314,0.00003337543,0.0000172002,0.0007780282,0.1364659,0.0102347,0.005051229,0.2639638,0.0007857081],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6585048,0.00000880609,0.3387102,0.0009186975,0.00006621426,0.0001132866,0.0001455515,0.00006760922,0.001464884],"genre_scores_gemma":[0.8955634,0.000002265862,0.1032751,0.0000808329,0.00005744918,5.423239e-7,0.00009756505,0.000003702562,0.0009191622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6157877,"threshold_uncertainty_score":0.3413796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02239467204610845,"score_gpt":0.2232793805288762,"score_spread":0.2008847084827677,"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."}}