{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007641824,0.0001340794,0.0002046056,0.0001979086,0.0005237,0.00009802851,0.0006150194,0.00009964863,0.000001715385],"category_scores_gemma":[0.004222182,0.0001325927,0.0002633253,0.001193007,0.00002243005,0.00007790944,0.0000435334,0.000122691,0.000009434714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002264489,"about_ca_system_score_gemma":0.0002055364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002066875,"about_ca_topic_score_gemma":0.000007225321,"domain_scores_codex":[0.9982146,0.0000661476,0.0005064255,0.0003587545,0.0005632214,0.0002908403],"domain_scores_gemma":[0.996015,0.001691136,0.0003701218,0.0003691354,0.001477049,0.00007761773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002650593,0.00006915171,0.0002015348,0.00003287923,0.00008007375,1.122026e-7,0.0004465889,0.9290329,0.00002003662,0.0660539,0.003574841,0.0004615157],"study_design_scores_gemma":[0.0006675228,0.00005390431,0.001275707,0.00001340029,0.0000654806,0.000001012039,0.00009541114,0.9495025,0.00022149,0.04233556,0.005613443,0.0001545738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001233446,0.00000785228,0.9948376,0.0009467769,0.000750252,0.0009283886,0.0005282107,0.000191167,0.0005763167],"genre_scores_gemma":[0.6668717,0.000002389283,0.3304531,0.0001361737,0.0002372963,0.00008582233,0.0001615741,0.00002181582,0.002030134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6656383,"threshold_uncertainty_score":0.5406973,"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."}}