{"id":"W6891893096","doi":"10.48550/arxiv.2407.06685","title":"Embark on DenseQuest: A System for Selecting the Best Dense Retriever for a Custom Collection","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Upload; Relevance (law); Ranking (information retrieval); Selection (genetic algorithm); Labrador Retriever; ENCODE","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002410768,0.00198504,0.001499976,0.002179647,0.001367928,0.002681672,0.002438494,0.001495933,0.02871751],"category_scores_gemma":[0.008031204,0.001048104,0.001254212,0.001648959,0.0006170821,0.00585347,0.004170807,0.00185981,0.03171113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009513453,"about_ca_system_score_gemma":0.001030979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00687703,"about_ca_topic_score_gemma":0.01054724,"domain_scores_codex":[0.9987539,0.000216818,0.00008818225,0.0003894052,0.0004262058,0.0001254034],"domain_scores_gemma":[0.9964282,0.001325742,0.0001616673,0.001103429,0.0005016443,0.0004793947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002320931,0.0007387045,0.01228836,0.001096576,0.0003639901,0.000759382,0.001351537,0.008298891,0.0321641,0.005711672,0.5433334,0.3915724],"study_design_scores_gemma":[0.0004943299,0.00109606,0.01269247,0.0002658187,0.0001823205,0.001371578,0.001325791,0.4605562,0.06989223,0.02750425,0.4239796,0.0006392839],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.04007734,0.001255468,0.2354993,0.0014071,0.0003686652,0.001111543,0.02117406,0.6731948,0.02591171],"genre_scores_gemma":[0.2253414,0.001002752,0.6219129,0.002264316,0.0004228674,0.001089013,0.07139446,0.0438933,0.03267897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02871751,"threshold_uncertainty_score":0.09606969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09180868196941877,"score_gpt":0.2253262716675246,"score_spread":0.1335175896981059,"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."}}