{"id":"W4392384312","doi":"10.1145/3616855.3635691","title":"Vector Search with OpenAI Embeddings: Lucene Is All You Need","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Ranking (information retrieval); Encoder; Information retrieval; Architecture; Artificial intelligence; Data mining; Geography; Operating system","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002269619,0.0001620456,0.0001768718,0.0002175346,0.00005821427,0.0005265208,0.00100475,0.00004714572,0.0002160753],"category_scores_gemma":[0.000008382429,0.0001133407,0.00007255951,0.001051004,0.00004416,0.000953363,0.0003962157,0.0001875161,0.0002921057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006731832,"about_ca_system_score_gemma":0.00007357819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009262301,"about_ca_topic_score_gemma":0.00001385717,"domain_scores_codex":[0.998491,0.00002593184,0.0001632861,0.0005783495,0.0004043959,0.0003370768],"domain_scores_gemma":[0.9990484,0.00005573854,0.00002018916,0.000674694,0.00009113762,0.0001099025],"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":[0.00003398997,0.0002135998,0.0005163676,0.0001572828,0.0007869788,0.0006079225,0.007288636,0.0003386248,0.03808334,0.617956,0.09653762,0.2374796],"study_design_scores_gemma":[0.0003564527,0.0005057637,0.000375941,0.0002049009,0.0000840151,0.0001021592,0.0002181015,0.4891378,0.3450621,0.01151039,0.1514101,0.001032226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003759014,0.0002725984,0.9770429,0.004118467,0.00005776676,0.0001671482,0.000001323647,0.001610422,0.01297043],"genre_scores_gemma":[0.6311846,0.00003735523,0.3592517,0.001302025,0.00005287447,0.00002374005,0.000001928433,0.00002372942,0.008122029],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6274256,"threshold_uncertainty_score":0.5077252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01888909085561529,"score_gpt":0.3146775010715027,"score_spread":0.2957884102158874,"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."}}