{"id":"W1525524375","doi":"10.1007/978-3-540-68123-6_46","title":"Evaluating Information Retrieval System Performance Based on Multi-grade Relevance","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Relevance (law); Computer science; Information retrieval; Rank (graph theory); Precision and recall; Relevance feedback; Learning to rank; Document retrieval; Measure (data warehouse); Recall; Data mining; Artificial intelligence; Mathematics; Ranking (information retrieval); Image retrieval; Psychology","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":[0.004730586,0.0006943439,0.001089712,0.003261995,0.0003756731,0.001962055,0.000573003,0.001458783,0.001870231],"category_scores_gemma":[0.03071233,0.0002290251,0.0007520238,0.001491612,0.0003252376,0.002334887,0.0007316466,0.0005413441,0.001388425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004533331,"about_ca_system_score_gemma":0.0003290159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508842,"about_ca_topic_score_gemma":0.001686739,"domain_scores_codex":[0.995595,0.001349719,0.0005280295,0.0004735438,0.001807368,0.0002463674],"domain_scores_gemma":[0.9655976,0.02721619,0.002098429,0.001288694,0.003108777,0.0006903328],"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":[0.02256324,0.002977565,0.2754014,0.001497841,0.002258719,0.0002670567,0.0004377219,0.03692907,0.1011317,0.0009531684,0.003803975,0.5517787],"study_design_scores_gemma":[0.0005271273,0.01810954,0.3453677,0.00007128697,0.002079871,0.0007988152,0.000387567,0.5254363,0.104129,0.001260322,0.00152405,0.0003084186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9815145,0.001513924,0.01267773,0.00009662992,0.00006533595,0.0001284041,0.0003534828,0.0005414431,0.003108534],"genre_scores_gemma":[0.9920643,0.0001676187,0.006103985,0.00001877976,0.00004492065,0.0000278397,0.0005198927,0.0000352394,0.001017341],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004730586,"threshold_uncertainty_score":0.02501804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.048144291722296,"score_gpt":0.2930885819025447,"score_spread":0.2449442901802487,"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."}}