{"id":"W2031979200","doi":"10.1016/j.ins.2013.06.019","title":"Weighting tags and paths in XML documents according to their topic generalization","year":2013,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Weighting; Computer science; Generalization; Information retrieval; XML; Data mining; Document Structure Description; Database; Mathematics; World Wide Web","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":[0.003039313,0.0008106418,0.0007687209,0.01059392,0.001094692,0.002639829,0.0007896376,0.00118577,0.002282655],"category_scores_gemma":[0.01471564,0.0005574703,0.001197628,0.008340877,0.0008329282,0.004805099,0.001601623,0.001655107,0.0009448373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001280509,"about_ca_system_score_gemma":0.002334284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007560228,"about_ca_topic_score_gemma":0.01386205,"domain_scores_codex":[0.997802,0.0005117883,0.000298021,0.0005396069,0.0006691501,0.000179466],"domain_scores_gemma":[0.9903737,0.005256074,0.0007188789,0.0008351931,0.002391367,0.0004248199],"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":[0.002528931,0.0005171368,0.1236347,0.001916125,0.0006019353,0.0007829019,0.006436334,0.02398169,0.07042203,0.03714393,0.01533921,0.7166952],"study_design_scores_gemma":[0.0005851669,0.001453817,0.1288785,0.001083276,0.003698697,0.003303323,0.008490203,0.3743203,0.07835824,0.2619931,0.1373865,0.0004488308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4690682,0.003313901,0.5052018,0.001142097,0.0004732568,0.001062838,0.01041845,0.004465376,0.004854149],"genre_scores_gemma":[0.4809938,0.00242603,0.497242,0.0002287484,0.0002693759,0.0005235227,0.01184624,0.000872356,0.005597945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01059392,"threshold_uncertainty_score":0.01607364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01434166746850803,"score_gpt":0.2454466806356847,"score_spread":0.2311050131671767,"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."}}