{"id":"W2296338095","doi":"10.1109/ichi.2015.98","title":"Golden Retriever: Question Retrieval System","year":2015,"lang":"en","type":"article","venue":"","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Heuristics; Computer science; Information retrieval; Semantic similarity; Relevance (law); Search engine indexing; Similarity (geometry); Semantics (computer science); Analytics; Semantic computing; Probabilistic latent semantic analysis; Data science; Artificial intelligence; Semantic Web","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":[0.002632278,0.001674351,0.001979832,0.006144335,0.000825977,0.001728982,0.002325566,0.001896415,0.03095141],"category_scores_gemma":[0.008422554,0.0007360718,0.001067634,0.002541402,0.0005097288,0.004329423,0.002526283,0.0009864776,0.03332787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009645596,"about_ca_system_score_gemma":0.001448633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003672155,"about_ca_topic_score_gemma":0.004029861,"domain_scores_codex":[0.9982382,0.0002991801,0.0002271683,0.0006188673,0.0004879597,0.0001286102],"domain_scores_gemma":[0.9970568,0.001034722,0.0002735923,0.0006129735,0.0007909298,0.0002309549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009144897,0.0003348002,0.003218174,0.0021661,0.0001640609,0.0005308581,0.0008475822,0.001361658,0.03551389,0.005505121,0.5290357,0.4204075],"study_design_scores_gemma":[0.0005816508,0.00106504,0.01007264,0.0004830187,0.0003617778,0.002623815,0.0009154335,0.1170857,0.1011836,0.0192503,0.7458377,0.0005393146],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.02752661,0.005512657,0.2679292,0.001224999,0.0005883095,0.002879887,0.05980181,0.5992402,0.03529637],"genre_scores_gemma":[0.1541406,0.002223415,0.5960613,0.00311461,0.0005973433,0.001780321,0.1790833,0.01210127,0.05089801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03095141,"threshold_uncertainty_score":0.1035428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03166001956969938,"score_gpt":0.2619031551959478,"score_spread":0.2302431356262484,"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."}}