{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001194287,0.0002064798,0.0001891002,0.0007990304,0.0002499904,0.0002212316,0.0004277678,0.0001171803,0.0004838625],"category_scores_gemma":[0.00079476,0.0002251171,0.00004737445,0.0008316177,0.0001712826,0.0004866048,0.00008615394,0.0002510219,0.00009604711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006055438,"about_ca_system_score_gemma":0.0002258685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001077101,"about_ca_topic_score_gemma":0.000005589315,"domain_scores_codex":[0.9982694,0.00001931318,0.0003377356,0.0002673496,0.0007482785,0.0003578996],"domain_scores_gemma":[0.9990787,0.00008800002,0.0001869197,0.0004372013,0.0001362538,0.00007294222],"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":[0.0000243417,0.00003229654,0.00001888851,0.0008802437,0.00007793749,0.000002190314,0.001143904,0.1808256,0.05024726,0.002351055,0.3690681,0.3953282],"study_design_scores_gemma":[0.0001838183,0.00003550152,0.000007221382,0.00004534822,0.00001810849,0.000004928526,0.0001394819,0.8215716,0.0006008782,0.0001208195,0.1770425,0.0002297006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.0006511199,0.0003268522,0.3734859,0.0002214261,0.004835573,0.002115302,0.0001682715,0.002900749,0.6152948],"genre_scores_gemma":[0.04760199,0.0001634487,0.8169451,0.0005146792,0.002178661,0.000102281,0.002104096,0.001589283,0.1288005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6407461,"threshold_uncertainty_score":0.9180009,"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."}}