{"id":"W4393089651","doi":"10.1007/978-3-031-56063-7_27","title":"BertPE: A BERT-Based Pre-retrieval Estimator for Query Performance Prediction","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Computer science; Estimator; Information retrieval; Data mining; Artificial intelligence; Statistics; Mathematics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00107927,0.0005652614,0.0005628756,0.00112058,0.0003721821,0.001043628,0.002820531,0.0003486403,0.00001188637],"category_scores_gemma":[0.0001414206,0.0005004644,0.0002594343,0.0009600482,0.0004587436,0.0008720625,0.0007571494,0.0007038513,0.00005051664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003145785,"about_ca_system_score_gemma":0.0009203042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001649033,"about_ca_topic_score_gemma":0.00002082523,"domain_scores_codex":[0.9957475,0.00001728662,0.0006107911,0.001922506,0.001018316,0.0006835836],"domain_scores_gemma":[0.9972124,0.0005722619,0.000237631,0.00152194,0.000260957,0.0001948831],"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":[0.00007676589,0.0000944784,0.0003007432,0.0007737573,0.0001128488,0.00008043842,0.000762686,0.2302289,0.0003242445,0.01737597,0.0006006649,0.7492685],"study_design_scores_gemma":[0.0002434833,0.0003137911,0.00008720982,0.0008373342,0.0000509632,0.00002955279,7.245487e-8,0.9775378,0.001457926,0.01524781,0.003687076,0.0005070529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003189903,0.0004706041,0.994453,0.0009468988,0.002253541,0.0004317775,0.00009166363,0.0003779677,0.0006555308],"genre_scores_gemma":[0.1940005,0.00005021003,0.7997096,0.001278824,0.001447087,0.00005794208,0.0001426183,0.0001077048,0.003205481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7487615,"threshold_uncertainty_score":0.9999934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01360314739372781,"score_gpt":0.2454020613334198,"score_spread":0.231798913939692,"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."}}