{"id":"W2058488627","doi":"10.14778/1687627.1687715","title":"Improved search for socially annotated data","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Scalability; Information retrieval; Annotation; Resource (disambiguation); Process (computing); Data mining; Similarity (geometry); Probabilistic logic; Cluster analysis; Machine learning; Database; 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":[0.0006633828,0.0001034821,0.0001645864,0.00006256553,0.0001555204,0.000152708,0.00324214,0.00003181325,0.000002061787],"category_scores_gemma":[0.00009828711,0.00007115716,0.0000808425,0.0004160153,0.00003428414,0.0004821251,0.0007623963,0.00008250232,0.000002111913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002940083,"about_ca_system_score_gemma":0.00007932559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003341731,"about_ca_topic_score_gemma":0.000001641776,"domain_scores_codex":[0.9988407,0.000004959543,0.000222724,0.0003853114,0.0002820482,0.0002642686],"domain_scores_gemma":[0.999098,0.0000320269,0.0001433433,0.0004562059,0.0002197718,0.00005067732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006753356,0.0005373074,0.0009715843,0.0001269123,0.0002844449,5.61453e-7,0.002615958,0.00002369658,0.5731775,0.1212131,0.05320947,0.2477719],"study_design_scores_gemma":[0.002453381,0.0007948562,0.004073026,0.0001667647,0.0002105917,0.00001130178,0.0006631932,0.3450712,0.6143347,0.01704398,0.01449512,0.0006818725],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4984266,0.001136367,0.2533619,0.2069218,0.001884441,0.006735269,0.001165004,0.001574882,0.02879371],"genre_scores_gemma":[0.9471116,0.0000182842,0.05183341,0.0004231009,0.00009657431,0.00001306128,0.00001693058,0.000006618399,0.0004804289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4486851,"threshold_uncertainty_score":0.6024757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04524835060069354,"score_gpt":0.2941844958611444,"score_spread":0.2489361452604509,"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."}}