{"id":"W2111814513","doi":"10.14778/2535570.2488330","title":"Partitioning and ranking tagged data sources","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Categorization; Partition (number theory); Set (abstract data type); Rank (graph theory); Learning to rank; Focus (optics); Data mining; Social media; Data science; World Wide Web; Artificial intelligence; Mathematics","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":[0.00804159,0.002282329,0.002735862,0.01137573,0.002632932,0.006833583,0.003752546,0.001962093,0.001557108],"category_scores_gemma":[0.0383774,0.001057092,0.002419512,0.01056466,0.001158815,0.006252288,0.004679221,0.002024939,0.001431141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002197189,"about_ca_system_score_gemma":0.003056327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004630052,"about_ca_topic_score_gemma":0.008232278,"domain_scores_codex":[0.987938,0.004128767,0.001075948,0.002284331,0.00377965,0.0007933388],"domain_scores_gemma":[0.9741278,0.01265836,0.00166928,0.005823409,0.004979663,0.0007415194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001224304,0.000735226,0.01925947,0.001526645,0.0006339095,0.0008254669,0.002480661,0.1916441,0.02106779,0.05672936,0.01561217,0.688261],"study_design_scores_gemma":[0.0001265544,0.0003819691,0.005728985,0.0002520471,0.0003070357,0.0007199006,0.002229237,0.8168458,0.01938878,0.1254565,0.02840181,0.0001613195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03783844,0.0007160653,0.9554579,0.0004765192,0.0001489785,0.0006673997,0.002109406,0.00101588,0.001569364],"genre_scores_gemma":[0.1598459,0.000499286,0.8268598,0.0001386421,0.0001785344,0.0006578898,0.009847344,0.0002795187,0.001692984],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01137573,"threshold_uncertainty_score":0.04252851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01660096490705265,"score_gpt":0.2322763896575149,"score_spread":0.2156754247504622,"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."}}