{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001928797,0.0005981227,0.0005238635,0.001404356,0.0007106728,0.0006436218,0.00290999,0.0003858741,0.00001013495],"category_scores_gemma":[0.0003329406,0.0005274386,0.0001617622,0.001143449,0.0004624853,0.002792901,0.0005875527,0.001261576,0.000311385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027831,"about_ca_system_score_gemma":0.00121874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000794614,"about_ca_topic_score_gemma":0.000002101469,"domain_scores_codex":[0.9942285,0.00006529117,0.001033091,0.0008854757,0.002964853,0.0008228187],"domain_scores_gemma":[0.9963586,0.0005269067,0.0006334374,0.001483147,0.0007637957,0.0002341163],"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":[0.00005637155,0.0000401987,0.00005659438,0.0002638165,0.000005202847,0.00003893813,0.00123274,0.3537008,0.00006120084,0.002108554,0.00002518322,0.6424104],"study_design_scores_gemma":[0.0007140742,0.0005318748,0.000428551,0.0008154935,0.000004963654,0.00007195248,3.684411e-7,0.9935001,0.002163865,0.00009936953,0.001065038,0.0006043527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001195501,0.00005735115,0.9935342,0.0002376305,0.001673922,0.0008196763,0.00001162406,0.0003650843,0.002105019],"genre_scores_gemma":[0.4403122,0.00007279476,0.5566771,0.00220652,0.0003148108,0.00002251648,0.00003733176,0.00003911968,0.0003176414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6418061,"threshold_uncertainty_score":0.9997177,"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."}}