{"id":"W3011864725","doi":"","title":"DescribeX: A Framework for Exploring and Querying XML Web Collections","year":2008,"lang":"en","type":"preprint","venue":"TSpace","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"XPath; Computer science; Automatic summarization; XML; Information retrieval; Path expression; Scalability; XML database; Streaming XML; Database; Key (lock); Search engine indexing; World Wide Web","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001557717,0.0002487628,0.0003416173,0.0001597231,0.000572907,0.0001607939,0.000307327,0.0001582572,0.000002833365],"category_scores_gemma":[0.0002229673,0.0002538234,0.00009269848,0.000290222,0.00006079871,0.000357336,0.001040177,0.0004203904,0.000004123921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008232054,"about_ca_system_score_gemma":0.0002151518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002604792,"about_ca_topic_score_gemma":0.00007040225,"domain_scores_codex":[0.9985954,0.00004128867,0.0002223919,0.0006534559,0.0001641353,0.0003233628],"domain_scores_gemma":[0.9985446,0.0002795655,0.0001596053,0.0008186235,0.0001006595,0.00009694728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000450987,0.00009288333,0.0002088314,0.001103406,0.000183531,0.0000693617,0.0347044,0.003484729,0.0006333107,0.926868,0.01874945,0.01385704],"study_design_scores_gemma":[0.0008134737,0.0001863307,0.0001299239,0.002861435,0.00005248198,0.0002625435,0.003559319,0.06357194,0.002415047,0.04638339,0.8778785,0.001885546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005422043,0.001079997,0.9895142,0.0006113457,0.00146602,0.0005490892,0.00003798694,0.0003377354,0.0009815971],"genre_scores_gemma":[0.01082343,0.001628264,0.9838489,0.0001071317,0.0003741705,0.0009594081,0.00001169813,0.00003287509,0.002214164],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8804846,"threshold_uncertainty_score":0.9999914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1304925359317852,"score_gpt":0.345237154838614,"score_spread":0.2147446189068288,"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."}}