{"id":"W3083669401","doi":"10.1145/3409256.3409818","title":"Approximate Nearest Neighbor Search and Lightweight Dense Vector Reranking in Multi-Stage Retrieval Architectures","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Blackberry (Canada)","funders":"","keywords":"Computer science; Nearest neighbor search; Context (archaeology); k-nearest neighbors algorithm; Pareto principle; Artificial intelligence; Pattern recognition (psychology); Point (geometry); Data mining; Mathematics; Mathematical optimization","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":[0.0008901317,0.0003905488,0.0007687535,0.0007982274,0.0004081202,0.001071721,0.001138491,0.0007734335,0.002859316],"category_scores_gemma":[0.002618997,0.0002876085,0.0004011934,0.001094196,0.0004496681,0.00261212,0.0006460444,0.0005742408,0.0009833098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005446165,"about_ca_system_score_gemma":0.0007334345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002943783,"about_ca_topic_score_gemma":0.00659079,"domain_scores_codex":[0.9993314,0.0001796812,0.00006093812,0.00009673997,0.0002395847,0.00009165831],"domain_scores_gemma":[0.9989673,0.0003805172,0.0001118637,0.000230331,0.0002657563,0.00004421389],"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":[0.0005136828,0.0003390355,0.00160895,0.0002638854,0.00006633272,0.0002090314,0.0002128957,0.3343301,0.0517232,0.0247441,0.002854383,0.5831344],"study_design_scores_gemma":[0.00002915999,0.0003038292,0.0004460785,0.00001073982,0.00002006569,0.0001393438,0.00004242899,0.9743619,0.0145474,0.008380736,0.001697727,0.00002065758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05894382,0.0006454129,0.9370081,0.0001297916,0.00002896236,0.00008165857,0.00004998748,0.0008970317,0.002215147],"genre_scores_gemma":[0.5823774,0.0003098302,0.4112436,0.00008028893,0.00005422605,0.0001049957,0.0001849251,0.00006156894,0.005583203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002943783,"threshold_uncertainty_score":0.009565413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0621761039109821,"score_gpt":0.3183940622263623,"score_spread":0.2562179583153802,"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."}}