{"id":"W2096249996","doi":"10.1145/1141753.1141818","title":"Using controlled query generation to evaluate blind relevance feedback algorithms","year":2006,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Query expansion; Query optimization; Web query classification; Relevance (law); Information retrieval; Sargable; Relevance feedback; Set (abstract data type); Query language; Process (computing); Web search query; Online aggregation; Data mining; Result set; Query by Example; Term (time); Algorithm; Search engine; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006232847,0.0001149469,0.000173333,0.0001446847,0.0001818132,0.0003375967,0.0003203077,0.00004947987,0.00006239542],"category_scores_gemma":[0.00005779899,0.00009016228,0.00006661979,0.0004650504,0.00001581663,0.0008456431,0.00009515354,0.00007845271,0.0003076569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008525179,"about_ca_system_score_gemma":0.0001124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001532879,"about_ca_topic_score_gemma":0.00002467858,"domain_scores_codex":[0.9985248,0.00006553107,0.0003741098,0.0002219814,0.0005374302,0.000276113],"domain_scores_gemma":[0.99914,0.00004590485,0.00007693517,0.0002901282,0.0003575245,0.00008948087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006752491,0.0005808244,0.0007956347,0.00003851559,0.0000678905,0.00005487754,0.001452008,0.1571144,0.3371141,0.1947639,0.02499033,0.2823523],"study_design_scores_gemma":[0.00259636,0.0000586599,0.0006028269,0.000005081906,0.000005850667,0.000008045408,0.000007518536,0.9775915,0.01686506,0.0002923041,0.00180488,0.0001619058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1924775,0.0000220195,0.8026686,0.0006521158,0.0003317473,0.0004838047,0.000001427808,0.0001026181,0.003260122],"genre_scores_gemma":[0.518294,0.000005497152,0.4705709,0.001527647,0.0004803836,0.00004928166,0.00001393882,0.00001156836,0.009046777],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8204771,"threshold_uncertainty_score":0.3954409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08124939581230618,"score_gpt":0.3355957155963968,"score_spread":0.2543463197840906,"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."}}