{"id":"W2002932370","doi":"10.1145/1061318.1061324","title":"Concise descriptions of subsets of structured sets","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Automatic summarization; Theoretical computer science; Set (abstract data type); Minimum description length; Online analytical processing; Hierarchy; Cover (algebra); Context (archaeology); Representation (politics); Data mining; Algorithm; Artificial intelligence; Data warehouse","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":[0.00221181,0.0006411542,0.001026165,0.002618103,0.0007449456,0.003211886,0.001784012,0.0009176666,0.00416925],"category_scores_gemma":[0.01179663,0.0007064867,0.001002792,0.004164882,0.001209973,0.00964782,0.001979602,0.001231166,0.0007707657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378297,"about_ca_system_score_gemma":0.0008772755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001106882,"about_ca_topic_score_gemma":0.001655707,"domain_scores_codex":[0.9971274,0.0009212605,0.0003468556,0.0004465827,0.0009473841,0.0002105905],"domain_scores_gemma":[0.9936215,0.003480811,0.0008641322,0.001112746,0.0007096498,0.0002111538],"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":[0.0002181742,0.00008357257,0.001282646,0.0006732363,0.00008319858,0.000565473,0.001424717,0.07523867,0.004728945,0.7949336,0.009184256,0.1115835],"study_design_scores_gemma":[0.00004785293,0.000148856,0.0005138396,0.0001562373,0.00007466788,0.0005333452,0.0007957797,0.2015044,0.005666014,0.7435764,0.04693099,0.00005169573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07561506,0.002277653,0.9070789,0.001566524,0.0001013536,0.0002128193,0.003597157,0.000788936,0.00876161],"genre_scores_gemma":[0.4650638,0.002031705,0.515063,0.0003682663,0.000219762,0.0005280953,0.007841733,0.000353566,0.008530146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00416925,"threshold_uncertainty_score":0.01394755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0319806076430219,"score_gpt":0.2639264952448165,"score_spread":0.2319458876017946,"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."}}