{"id":"W3055273286","doi":"10.1109/tvcg.2020.3030387","title":"VizCommender: Computing Text-Based Similarity in Visualization Repositories for Content-Based Recommendations","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Visualization; Relevance (law); Information retrieval; Similarity (geometry); Visual analytics; Latent Dirichlet allocation; Similarity measure; Analytics; Tag cloud; Topic model; Data science; Measure (data warehouse); Recommender system; Information visualization; World Wide Web; Data mining; Artificial intelligence; Image (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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005964802,0.0006514424,0.0007207795,0.001137875,0.0006601138,0.00111979,0.000830919,0.0005042232,0.000008504866],"category_scores_gemma":[0.00003972392,0.0007523995,0.0003108653,0.001576583,0.0001295103,0.0004396131,0.00005263037,0.0006309933,0.000002691395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001485329,"about_ca_system_score_gemma":0.0003820812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005735455,"about_ca_topic_score_gemma":0.0001071803,"domain_scores_codex":[0.995838,0.0004986571,0.001277998,0.001385862,0.0005541849,0.0004452668],"domain_scores_gemma":[0.9970871,0.0005833774,0.0006382812,0.000787308,0.0006304353,0.0002734687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000142032,0.002201004,0.0006716482,0.00131604,0.0002392905,0.00001247804,0.001845523,0.06308799,0.00004344999,0.9162491,0.003025001,0.01116646],"study_design_scores_gemma":[0.001869664,0.0003180671,0.0001492165,0.000474321,0.00008377913,0.000002310789,0.0000706971,0.9904952,0.002092771,0.001332179,0.00237883,0.0007329721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003936408,0.0000414093,0.9930826,0.002161575,0.002197687,0.001153431,0.0002847581,0.0006715679,0.00001329724],"genre_scores_gemma":[0.9364959,0.0002153082,0.0448501,0.01570207,0.0002792627,0.0002097914,0.002081419,0.0001351215,0.00003104278],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9482325,"threshold_uncertainty_score":0.9999171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07907896541989255,"score_gpt":0.3382526641997582,"score_spread":0.2591736987798656,"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."}}