{"id":"W4388748447","doi":"10.48550/arxiv.2311.09175","title":"Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pipeline (software); Ranking (information retrieval); Artificial intelligence; Fuse (electrical); Filter (signal processing); Weighting; Query expansion; Data mining; Information retrieval; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004643931,0.00185853,0.001525364,0.001705408,0.0005616238,0.001277382,0.001932029,0.001442538,0.003779436],"category_scores_gemma":[0.01505555,0.000554329,0.001038184,0.001055401,0.0008945441,0.004413844,0.002185731,0.001894727,0.003450559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009670698,"about_ca_system_score_gemma":0.001205741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005694448,"about_ca_topic_score_gemma":0.009114705,"domain_scores_codex":[0.9973808,0.0008301227,0.0001847977,0.0007503926,0.0005775576,0.0002763369],"domain_scores_gemma":[0.9943681,0.002355738,0.0003084472,0.001695976,0.001037839,0.0002338723],"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":[0.001313599,0.001150715,0.01265135,0.0005883114,0.0003930164,0.000349879,0.0004645816,0.09775239,0.0445356,0.006225169,0.02350454,0.8110709],"study_design_scores_gemma":[0.0001429035,0.00104646,0.005880026,0.00005927921,0.0002242634,0.0005972121,0.0002308597,0.941507,0.03387341,0.00821428,0.00811054,0.0001138372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3897842,0.00723366,0.5612608,0.001806216,0.0005411598,0.0004251729,0.001822744,0.02572457,0.01140148],"genre_scores_gemma":[0.8650482,0.0008093751,0.1184992,0.001091764,0.0002523427,0.0001392995,0.003217879,0.0006375272,0.01030446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005694448,"threshold_uncertainty_score":0.02455974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09350871488186248,"score_gpt":0.2233487573134619,"score_spread":0.1298400424315994,"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."}}