{"id":"W4400529018","doi":"10.1145/3626772.3657979","title":"Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?","year":2024,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Generalization; Encoder; Query expansion; Artificial intelligence; Data mining; Information retrieval; Mathematics; Operating system","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":[0.00008464105,0.00006845772,0.00006632186,0.00006346332,0.00007833273,0.0001075672,0.0002401723,0.00003824491,0.00004081737],"category_scores_gemma":[0.000004451981,0.00005773684,0.0000461662,0.0003230249,0.00003608072,0.0004064284,0.00008637512,0.00005176376,0.0000157693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003187288,"about_ca_system_score_gemma":0.0001055459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000209422,"about_ca_topic_score_gemma":0.00002067338,"domain_scores_codex":[0.9992819,0.00001402387,0.0001772095,0.0002553666,0.0001538345,0.0001176297],"domain_scores_gemma":[0.9995428,0.00002660239,0.0000276975,0.0002829653,0.00007983846,0.00004012844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.996996e-7,0.00004032858,0.0003611968,0.00003090511,0.00001252699,0.000001864545,0.0003273464,0.003287956,0.02318128,0.9530514,0.002146497,0.01755782],"study_design_scores_gemma":[0.000100986,0.00002786282,0.002564186,0.00001636176,0.000003961554,0.000004485531,0.00002671247,0.9747804,0.01010258,0.01031158,0.001955278,0.00010559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01525775,0.0002548119,0.9807074,0.001233658,0.0003109123,0.0001107353,0.000009583747,0.0001721993,0.001942921],"genre_scores_gemma":[0.9289821,0.00002896278,0.06787795,0.00008367002,0.0001023777,0.00002776169,0.00001533499,0.00000683806,0.002874943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714925,"threshold_uncertainty_score":0.235444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01224747830565552,"score_gpt":0.2762828888245987,"score_spread":0.2640354105189432,"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."}}