{"id":"W2132314908","doi":"10.1145/1390334.1390446","title":"Novelty and diversity in information retrieval evaluation","year":2008,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":951,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Novelty; Computer science; Redundancy (engineering); Ranking (information retrieval); Information retrieval; Ambiguity; Learning to rank; Information gain; Data mining; Artificial intelligence; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0005864014,0.0000441987,0.00005087314,0.0001483768,0.0001905837,0.0000449162,0.0001677648,0.00003428003,0.00003569388],"category_scores_gemma":[0.00007728459,0.00003846972,0.00001217311,0.000353456,0.00002648174,0.00323071,0.0003195558,0.00006932268,0.00006173304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005780931,"about_ca_system_score_gemma":0.00006497626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007839203,"about_ca_topic_score_gemma":0.000006013852,"domain_scores_codex":[0.9991736,0.00002641366,0.0001477673,0.00006517081,0.0004797172,0.0001073607],"domain_scores_gemma":[0.9996206,0.00002016933,0.00003514847,0.0001120437,0.0001670652,0.00004497731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001932684,0.0002231339,0.4530937,0.00006083758,0.00001499189,0.00002113469,0.0595904,0.0004501252,0.0004150883,0.1370026,0.003508249,0.3454265],"study_design_scores_gemma":[0.0008574483,0.00004674354,0.8110272,0.000002848722,0.000001465147,0.00002308183,0.00007373995,0.1860925,0.0006746049,0.0004544698,0.0006477935,0.00009810493],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9325886,0.000005677442,0.05964412,0.000297883,0.00007644672,0.0002006339,0.000001042284,0.00004894998,0.007136602],"genre_scores_gemma":[0.9968899,0.00001305939,0.002760035,0.0002566149,0.000004564793,0.000001271762,0.000005108865,4.67865e-7,0.00006897611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3579335,"threshold_uncertainty_score":0.2342186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0679627973098831,"score_gpt":0.2735590934351592,"score_spread":0.2055962961252761,"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."}}