{"id":"W6891802063","doi":"10.48448/am9m-es87","title":"Evaluating Embedding APIs for Information Retrieval","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Embedding; Domain (mathematical analysis); Generalization; Order (exchange); Language model; Key (lock)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01492247,0.002451776,0.001875447,0.006675685,0.0009270533,0.004886794,0.001855071,0.002392608,0.003375785],"category_scores_gemma":[0.06971598,0.0004709366,0.001548228,0.005688868,0.001114823,0.008237348,0.002998064,0.001729254,0.002409669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00199316,"about_ca_system_score_gemma":0.00171815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008265263,"about_ca_topic_score_gemma":0.008181256,"domain_scores_codex":[0.9793406,0.010926,0.00235563,0.001387617,0.005251574,0.0007386167],"domain_scores_gemma":[0.9688204,0.01977036,0.001679711,0.005205176,0.003916949,0.000607379],"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":[0.003619466,0.001928641,0.0179355,0.00333223,0.001077604,0.0002486151,0.0004695496,0.1481184,0.00901954,0.01400134,0.04563922,0.7546098],"study_design_scores_gemma":[0.0002268268,0.001546196,0.005241963,0.0001536001,0.0002598495,0.0002105092,0.00030988,0.961446,0.01078118,0.01017311,0.009545554,0.0001052963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5386047,0.02389637,0.3215575,0.003064902,0.001345698,0.001995677,0.009376269,0.06197472,0.03818417],"genre_scores_gemma":[0.7796206,0.002445742,0.1945576,0.0004692033,0.0003463604,0.0006934429,0.01729823,0.001366637,0.003202151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01492247,"threshold_uncertainty_score":0.07891852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04511703273861628,"score_gpt":0.3456165370082905,"score_spread":0.3004995042696742,"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."}}