{"id":"W4400524635","doi":"10.1145/3626772.3657674","title":"Embark on DenseQuest: A System for Selecting the Best Dense Retriever for a Custom Collection","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Upload; Relevance (law); Ranking (information retrieval); Labrador Retriever; Information retrieval; Selection (genetic algorithm); Data collection; ENCODE; Cloud computing; World Wide Web; Data science; Artificial intelligence; Operating system","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":[0.000648597,0.0001095101,0.0001077931,0.00008968278,0.0003500148,0.0004294285,0.0003175546,0.00006510809,0.000001276084],"category_scores_gemma":[0.0001400831,0.00007365806,0.00009438607,0.0004599598,0.000009111667,0.0001673912,0.00005160299,0.0001051055,0.00002315426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002391061,"about_ca_system_score_gemma":0.0001460747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004752744,"about_ca_topic_score_gemma":0.00003765386,"domain_scores_codex":[0.9989411,0.00003772056,0.0001986282,0.0004052794,0.0001640776,0.0002531574],"domain_scores_gemma":[0.9988297,0.0006470597,0.00003456012,0.0003194325,0.0001294034,0.00003982154],"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":[0.0001200172,0.00005791681,0.00005945003,0.001007724,0.0001521163,0.00002161465,0.006577896,0.002539854,0.004597075,0.9061386,0.02601765,0.05271007],"study_design_scores_gemma":[0.0001839457,0.0001753203,0.000002933669,0.0001563142,0.0000187904,0.00007700959,0.0002260511,0.9782934,0.005931979,0.001633854,0.01318268,0.0001177124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01663536,0.0001279875,0.9776324,0.001507584,0.001322565,0.0008724662,0.00000187852,0.000478041,0.001421689],"genre_scores_gemma":[0.9456767,0.000001952122,0.04843451,0.0002757705,0.0003353278,0.0002532748,6.95641e-7,0.00001828798,0.005003519],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9757535,"threshold_uncertainty_score":0.4140989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03449104065488361,"score_gpt":0.2781984682090163,"score_spread":0.2437074275541327,"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."}}