{"id":"W2092683383","doi":"10.1145/584792.584867","title":"Discovering approximate keys in XML data","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; XML; Key (lock); Information retrieval; Document Structure Description; Set (abstract data type); Representation (politics); XML validation; XML database; Well-formed document; Streaming XML; Search engine indexing; XML Encryption; Data mining; Theoretical computer science; World Wide Web; Programming language; Computer security","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":[0.0001510021,0.00005786166,0.00005914446,0.00006010133,0.00002169881,0.0002599561,0.001976789,0.000009622602,0.00009981386],"category_scores_gemma":[0.00000859152,0.00004830179,0.000007768351,0.0002495216,0.000009440156,0.002380921,0.002077694,0.00004264036,0.0002256392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007184534,"about_ca_system_score_gemma":0.000001520402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005511685,"about_ca_topic_score_gemma":0.00002953352,"domain_scores_codex":[0.9992915,0.000009730958,0.00009710957,0.0003120319,0.0001192485,0.0001703217],"domain_scores_gemma":[0.9988229,0.00001101975,0.00001637829,0.001122635,0.000002693454,0.00002440999],"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":[7.248675e-7,0.000211541,0.002194106,0.00003334843,0.00001430589,0.0001057956,0.0004686862,0.000118526,0.00005261711,0.2232683,0.0359207,0.7376114],"study_design_scores_gemma":[0.0001357976,0.000005487416,0.0004993644,0.000005825838,7.288396e-7,9.308382e-7,0.000022856,0.9821584,0.00003627523,0.0007428515,0.01630047,0.0000910247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001586168,0.00005925712,0.9094273,0.001415258,0.0002115745,0.00009746827,0.00000722279,0.000162149,0.08703353],"genre_scores_gemma":[0.5971149,0.000194128,0.3844402,0.0008942059,0.0001376699,0.00001286904,0.00009034307,0.00001598905,0.01709962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9820399,"threshold_uncertainty_score":0.3673399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08292524527261654,"score_gpt":0.2532951234127986,"score_spread":0.1703698781401821,"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."}}