{"id":"W2049769908","doi":"10.1007/bf02960771","title":"Clustering DTDs: An interactive two-level approach","year":2002,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Cluster analysis; Document type definition; Document Structure Description; XML; Information retrieval; Data mining; Artificial intelligence","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":[0.0009597579,0.0001423173,0.0002582693,0.001333222,0.0002547764,0.0003389143,0.002619028,0.00006722371,0.00000285718],"category_scores_gemma":[0.00009756647,0.0001171888,0.00003125159,0.001966292,0.0006663621,0.00285222,0.001440338,0.0005228734,0.000005411373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001180198,"about_ca_system_score_gemma":0.00009660588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002422557,"about_ca_topic_score_gemma":0.000001025626,"domain_scores_codex":[0.9980512,0.00004307957,0.0003489206,0.0004195138,0.0006829623,0.0004543018],"domain_scores_gemma":[0.9981445,0.00005839331,0.0002458945,0.0005211963,0.0008327311,0.0001972548],"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":[0.000004487475,0.0001232512,0.00008498118,0.000007246585,0.00001213028,0.00009236856,0.0007865646,0.001182045,0.002608196,0.002555326,0.00004415321,0.9924992],"study_design_scores_gemma":[0.0005168344,0.0006939453,0.0002184997,0.00002986213,0.000002187575,0.00320455,0.00008420119,0.9901481,0.001777017,0.002844765,0.0003368813,0.0001431156],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03122795,0.0001414915,0.9664255,0.001381562,0.0004007778,0.00007232195,3.212776e-7,0.00008548553,0.0002646036],"genre_scores_gemma":[0.4725325,0.00002565304,0.527236,0.00009289015,0.000088897,0.000001632577,2.561068e-8,0.000004520719,0.00001788266],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9923561,"threshold_uncertainty_score":0.486685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04570929441094207,"score_gpt":0.3133056358307519,"score_spread":0.2675963414198099,"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."}}