{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002589322,0.0001438858,0.0002386991,0.0002566489,0.00009024883,0.00005214967,0.001250279,0.00004169544,0.00005542114],"category_scores_gemma":[0.00002067352,0.0001340711,0.00008135671,0.0004759157,0.00005867845,0.001021411,0.00004034056,0.0001115126,0.00004463801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003035391,"about_ca_system_score_gemma":0.00003956522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001868103,"about_ca_topic_score_gemma":0.00007351698,"domain_scores_codex":[0.9986135,0.00007531949,0.0004374945,0.0003142164,0.0003656296,0.000193843],"domain_scores_gemma":[0.9977255,0.00008150355,0.0001683279,0.001856845,0.00008732885,0.00008051918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001520326,0.002649009,0.000401355,0.001704478,0.001111698,0.00006369471,0.002844628,0.03404836,0.05311339,0.1042902,0.03320691,0.7664143],"study_design_scores_gemma":[0.009017816,0.0009330284,0.003582539,0.001729766,0.0006193956,0.0002020332,0.001961514,0.5726355,0.1795072,0.00119883,0.2260464,0.002566045],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007239223,0.0001776432,0.988696,0.0002694101,0.0007559824,0.0003559746,0.002066163,0.0001017754,0.0003378238],"genre_scores_gemma":[0.9371369,0.000054775,0.06227939,0.00004152769,0.00003382045,0.00002640478,0.0001421772,0.00001002765,0.000274936],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9298977,"threshold_uncertainty_score":0.5467262,"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."}}