{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007936466,0.0002847177,0.000269747,0.0003522582,0.0006909571,0.0004704781,0.001053294,0.000296163,0.000002228191],"category_scores_gemma":[0.0001431853,0.000240934,0.0003455772,0.001095477,0.00005657884,0.0002213372,0.0007324871,0.0006323509,0.00009975668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008595528,"about_ca_system_score_gemma":0.0005439796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007003451,"about_ca_topic_score_gemma":0.00002507506,"domain_scores_codex":[0.9982868,0.0001052467,0.000279352,0.000738071,0.000165883,0.0004246398],"domain_scores_gemma":[0.9978985,0.0004499104,0.0002278114,0.0006806285,0.0006238334,0.0001193654],"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":[0.001164851,0.0002132525,0.0002619804,0.003206115,0.0004503995,0.0002157072,0.005734705,0.04503796,0.000378339,0.9304842,0.009453228,0.003399303],"study_design_scores_gemma":[0.0007885592,0.0004655112,0.00004398881,0.0005010287,0.0002334266,0.00003839492,0.0007400339,0.9788855,0.002513683,0.010936,0.004342547,0.0005113169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3641786,0.00005083188,0.6275436,0.0004295997,0.002480608,0.003196934,0.00009487937,0.0005830278,0.001441965],"genre_scores_gemma":[0.993169,0.00001563931,0.001058072,0.000104688,0.0001602608,0.00003262544,0.00001634614,0.00002410394,0.005419285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9338475,"threshold_uncertainty_score":0.9825002,"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."}}