{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006148611,0.001543952,0.002666839,0.005093778,0.001517797,0.003340713,0.003019277,0.002620788,0.00291102],"category_scores_gemma":[0.02888999,0.0007921253,0.001559546,0.006476096,0.001105258,0.005898339,0.005734315,0.001419279,0.001860921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002024696,"about_ca_system_score_gemma":0.00320291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008264619,"about_ca_topic_score_gemma":0.01307308,"domain_scores_codex":[0.9914664,0.003782222,0.000516582,0.001714106,0.00214165,0.0003790082],"domain_scores_gemma":[0.9887931,0.006161369,0.0008281162,0.002666073,0.001319685,0.0002317631],"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":[0.0007663133,0.0005554765,0.006869484,0.0009426858,0.0003832116,0.0006717971,0.001652628,0.3794012,0.01098552,0.09670877,0.0217577,0.4793051],"study_design_scores_gemma":[0.00002588031,0.00005505006,0.0003774893,0.00001829356,0.00002686684,0.00007900206,0.000201291,0.9592072,0.001507434,0.03534577,0.003134759,0.00002095219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04562248,0.001080117,0.9433795,0.001210745,0.00008281755,0.0001916929,0.001681642,0.003287903,0.00346317],"genre_scores_gemma":[0.3311459,0.0005093559,0.6563451,0.0003845627,0.0001604278,0.0003600219,0.006554449,0.0004254505,0.004114712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008264619,"threshold_uncertainty_score":0.03251731,"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."}}