{"id":"W4411403538","doi":"10.1145/3725325","title":"MIRAGE-ANNS: Mixed Approach Graph-based Indexing for Approximate Nearest Neighbor Search","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Search engine indexing; Computer science; Graph; Nearest neighbor search; k-nearest neighbors algorithm; Data mining; Search engine; Context (archaeology); Search algorithm; Theoretical computer science; Machine learning; Artificial intelligence; Algorithm; Information retrieval","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001050344,0.0001891584,0.0002661807,0.0002745615,0.0001467608,0.0001362708,0.01145339,0.00005261897,8.80191e-7],"category_scores_gemma":[0.0003363953,0.0001433404,0.000103549,0.001225233,0.0001248497,0.0009386893,0.007456416,0.0001583971,5.374391e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003438451,"about_ca_system_score_gemma":0.00003183818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005631419,"about_ca_topic_score_gemma":1.267835e-7,"domain_scores_codex":[0.9981697,0.00001146122,0.0003745825,0.0006589313,0.0004774935,0.000307819],"domain_scores_gemma":[0.9970763,0.0001130467,0.0002591551,0.002287248,0.0002306505,0.00003356807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004824206,0.0009930077,0.002179556,0.01060391,0.0005164978,0.000001595623,0.000162672,0.0001977213,0.007933303,0.7241876,0.04306589,0.2096758],"study_design_scores_gemma":[0.002932771,0.0005760807,0.003529876,0.002434548,0.0002557175,0.000001197517,0.0006180526,0.1622672,0.6098312,0.2015322,0.01529101,0.0007302313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002484276,0.0001319106,0.9875416,0.001959308,0.00009591965,0.001730341,0.00007189691,0.000182574,0.005802239],"genre_scores_gemma":[0.1642654,0.00007255717,0.8348446,0.0003089953,0.0000168894,0.00009290465,0.00002790666,0.00001792389,0.00035286],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6018978,"threshold_uncertainty_score":0.9938951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08133916376663859,"score_gpt":0.3436731363883481,"score_spread":0.2623339726217095,"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."}}