{"id":"W2369187457","doi":"","title":"Improved Algorithm of XML Document Structural Clustering Based on Edit Distance","year":2008,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; XML; Data mining; Node (physics); Document Structure Description; Algorithm; Reduction (mathematics); Similarity (geometry); Nesting (process); Repetition (rhetorical device); Edit distance; Hierarchical clustering; XML Schema (W3C); Tree structure; Theoretical computer science; Artificial intelligence; XML Signature; World Wide Web; Binary tree; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006040496,0.0001914818,0.0001948128,0.0001149472,0.0002983666,0.00004123764,0.0009505153,0.00005115155,0.000005520486],"category_scores_gemma":[4.770784e-7,0.0001904209,0.00009984186,0.0004924274,0.00008995197,0.0001969597,0.0002140976,0.0001359642,0.00001305542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008240894,"about_ca_system_score_gemma":0.00006710691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007771788,"about_ca_topic_score_gemma":0.000001621503,"domain_scores_codex":[0.9986359,0.00001914416,0.0003789294,0.0005145802,0.0002170969,0.0002342789],"domain_scores_gemma":[0.9987802,0.0000966707,0.000197032,0.0006742605,0.0001623281,0.0000895105],"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":[0.00001089393,0.0003147469,0.00005909168,0.00005469874,0.00003490286,0.000004690318,0.0002769198,0.04971099,0.008849452,0.102652,0.002135211,0.8358964],"study_design_scores_gemma":[0.0003408304,0.00007344146,0.0005472143,0.00001813612,0.000004007131,0.00002533096,0.000002164091,0.8946176,0.00874239,0.01056523,0.08480216,0.0002614509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001945534,0.00003096036,0.9977143,0.0007293024,0.00002854482,0.0007377447,0.00002635244,0.0002908689,0.0002474154],"genre_scores_gemma":[0.1121042,0.000007383254,0.8864657,0.0005981646,0.0001321668,0.0005793539,0.00003395641,0.00001420053,0.00006481826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8449066,"threshold_uncertainty_score":0.7765141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008390255096905322,"score_gpt":0.2563898193448937,"score_spread":0.2479995642479884,"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."}}