{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004115103,0.0003195498,0.0003288739,0.0005457737,0.0003607257,0.0003244879,0.001190494,0.0001996578,0.00003204678],"category_scores_gemma":[0.0001741141,0.0003672602,0.0000934414,0.001746366,0.0002066776,0.0005627038,0.002432858,0.000514474,0.0002223072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002395326,"about_ca_system_score_gemma":0.0003380829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001580066,"about_ca_topic_score_gemma":0.0004545066,"domain_scores_codex":[0.997318,0.0001861447,0.0002437548,0.001569639,0.0001742351,0.0005081939],"domain_scores_gemma":[0.9975179,0.000255204,0.0002125477,0.001445163,0.0002945303,0.0002746652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002023912,0.00009471481,0.005985045,0.0000686779,0.00016887,0.002411097,0.001909149,0.9033239,0.00163407,0.0833251,0.0002194686,0.0006574721],"study_design_scores_gemma":[0.0004543595,0.0002184003,0.004055812,0.0002940657,0.0001987207,0.00005847223,0.001596681,0.9338143,0.01414431,0.04350965,0.0004650883,0.001190093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5600832,0.00002060448,0.4382852,0.0003517479,0.0003065492,0.0003275748,0.000009555083,0.0002643374,0.0003512018],"genre_scores_gemma":[0.9889435,0.00008756943,0.007707516,0.00007666065,0.00005556752,9.121765e-7,0.000009983629,0.00003513324,0.003083114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4305777,"threshold_uncertainty_score":0.9998779,"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."}}