{"id":"W6929298606","doi":"10.48448/gr5e-ky21","title":"Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Redundancy (engineering); Pattern recognition (psychology); Compression (physics); Principal component analysis; Simple (philosophy); Data compression; Dimension (graph theory); Ranking (information retrieval); Pipeline (software)","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":[0.0007183498,0.001099217,0.000830663,0.002317332,0.0005692238,0.001011152,0.001239246,0.0006550832,0.006452588],"category_scores_gemma":[0.005788572,0.0002967938,0.0007988156,0.003210985,0.0005941783,0.002384664,0.001554508,0.000965691,0.005523419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004299238,"about_ca_system_score_gemma":0.001381691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003046883,"about_ca_topic_score_gemma":0.004599999,"domain_scores_codex":[0.9993263,0.0001389975,0.0000710828,0.0001211683,0.0002666331,0.0000757227],"domain_scores_gemma":[0.9983719,0.0004158474,0.0001218473,0.0005682507,0.0004649163,0.00005727439],"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":[0.0002943255,0.0001994539,0.0011555,0.000304799,0.00005912936,0.0001655761,0.0002109076,0.01086864,0.05411104,0.007427027,0.0268961,0.8983076],"study_design_scores_gemma":[0.0002779358,0.0009615016,0.005375755,0.0001220832,0.0001733016,0.001642305,0.0006027198,0.7169762,0.1894505,0.03302936,0.05121621,0.0001720842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05838585,0.001354668,0.9189932,0.0004912515,0.0003144235,0.0005009795,0.002548921,0.01391652,0.003494132],"genre_scores_gemma":[0.2251074,0.0008710255,0.7543684,0.0003519037,0.000274748,0.0005905787,0.01000056,0.0008878984,0.007547425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006452588,"threshold_uncertainty_score":0.02158606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01251257942419126,"score_gpt":0.2838892436625145,"score_spread":0.2713766642383232,"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."}}