{"id":"W4389261129","doi":"10.48550/arxiv.2311.18503","title":"End-to-End Retrieval with Learned Dense and Sparse Representations Using Lucene","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inference; Information retrieval; Implementation; Encoder; Software; Similarity (geometry); Artificial neural network; Artificial intelligence; Data mining; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001171925,0.000850789,0.0007007275,0.001123775,0.0005860053,0.00255065,0.002305461,0.001349902,0.008790427],"category_scores_gemma":[0.006248568,0.0005380225,0.0008321365,0.001059543,0.0009156517,0.006143916,0.002404064,0.001710478,0.006629227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001409143,"about_ca_system_score_gemma":0.001249637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009242526,"about_ca_topic_score_gemma":0.01733395,"domain_scores_codex":[0.9992208,0.0001654214,0.00005443923,0.0002052653,0.0002654076,0.00008862402],"domain_scores_gemma":[0.9988187,0.0004444126,0.00007450559,0.0004393641,0.0001801819,0.00004275976],"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":[0.001055998,0.000491952,0.001926713,0.0005863908,0.0002041165,0.0004824257,0.0005574552,0.2353343,0.02729443,0.1456818,0.0538715,0.532513],"study_design_scores_gemma":[0.00005392814,0.00006011811,0.0001976652,0.00002349394,0.00001861871,0.00008009379,0.00004644947,0.9284853,0.01525559,0.04475217,0.01099105,0.000035664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01220111,0.0003053556,0.9441363,0.0003857769,0.00003631142,0.0000868678,0.0007948944,0.03599125,0.006062127],"genre_scores_gemma":[0.2518695,0.0005455154,0.7223045,0.0004973596,0.00006436898,0.000299026,0.005541193,0.002290046,0.01658846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009242526,"threshold_uncertainty_score":0.02940691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2276242512458895,"score_gpt":0.2598679974942302,"score_spread":0.03224374624834075,"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."}}