{"id":"W4382449327","doi":"10.1162/tacl_a_00556","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Language model; Security token; Aggregate (composite); Exploit; Overhead (engineering); Encoder; Code (set theory); Artificial intelligence; Natural language processing; Set (abstract data type); Machine learning; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001846006,0.001847586,0.001556373,0.002408703,0.0006698607,0.001710632,0.003688904,0.001475402,0.01062227],"category_scores_gemma":[0.006045006,0.0007738376,0.001489315,0.001920859,0.001055231,0.004681627,0.003638043,0.002208554,0.007996951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009156452,"about_ca_system_score_gemma":0.001689172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007731715,"about_ca_topic_score_gemma":0.01311705,"domain_scores_codex":[0.998899,0.0002898141,0.0000851709,0.0003781806,0.0002155893,0.0001323288],"domain_scores_gemma":[0.9983304,0.0005434905,0.0001083593,0.0006124005,0.0003072886,0.00009797362],"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":[0.0004732493,0.0004307414,0.001346483,0.0003649699,0.0001548788,0.0003645771,0.0004173906,0.09544717,0.02470934,0.01588338,0.03080574,0.8296021],"study_design_scores_gemma":[0.00006738585,0.0002031749,0.0002706144,0.00002984087,0.00005821669,0.0001783079,0.000115613,0.9597753,0.01249564,0.0169566,0.009801117,0.0000482389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02090739,0.0006843304,0.9396949,0.0004042812,0.0002389269,0.0003476829,0.001111925,0.03407427,0.002536218],"genre_scores_gemma":[0.2603454,0.0004505809,0.720184,0.0005412574,0.0002004548,0.0005298983,0.005105868,0.002249437,0.01039321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01062227,"threshold_uncertainty_score":0.03553504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04200530028915431,"score_gpt":0.2897842792160807,"score_spread":0.2477789789269264,"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."}}