{"id":"W4241069479","doi":"10.1145/773153.773166","title":"Concise descriptions of subsets of structured sets","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Online analytical processing; Set (abstract data type); XML; Context (archaeology); Theoretical computer science; String (physics); Hierarchy; Focus (optics); Cover (algebra); Representation (politics); Simple (philosophy); Data mining; Information retrieval; Data warehouse; Mathematics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0000871761,0.00005761358,0.0001333144,0.00004012982,0.00002556662,0.000004118795,0.000142246,0.00002100136,0.0000599909],"category_scores_gemma":[0.00004784296,0.00004552024,0.00003227268,0.0001755202,0.00004863375,0.0002900858,0.00003897982,0.00002688429,0.000003685934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006169042,"about_ca_system_score_gemma":0.00004484172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003668011,"about_ca_topic_score_gemma":0.00004173025,"domain_scores_codex":[0.999429,0.00003400188,0.0002019727,0.0001216908,0.0001189622,0.00009431034],"domain_scores_gemma":[0.9993603,0.00002640881,0.00008916584,0.0003942648,0.00009287779,0.00003704613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001103734,0.00001205908,0.0005405038,0.00001746733,0.000005663119,0.000001256039,0.0002025126,0.00003552888,0.01747376,0.9801196,0.000559978,0.001030562],"study_design_scores_gemma":[0.001295252,0.0001760575,0.01012393,0.00009632817,0.00001505478,0.00008837201,0.0006958549,0.002936227,0.8672736,0.02261388,0.09419598,0.0004894206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05087606,0.0001358929,0.9441755,0.00001979754,0.0002006337,0.00008356194,0.00003522362,0.00003088388,0.004442427],"genre_scores_gemma":[0.7468753,0.000004226775,0.2529316,0.00002277158,0.000002346884,0.00000195001,0.000002299867,0.00000205102,0.0001574758],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9575058,"threshold_uncertainty_score":0.1856261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0193593033298114,"score_gpt":0.2505560855886307,"score_spread":0.2311967822588193,"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."}}