{"id":"W4391680357","doi":"10.1145/3640460","title":"Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Transformer; Search engine indexing; Inference; ENCODE; Artificial intelligence; Question answering; Information retrieval; Machine learning; Natural language processing; Voltage","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005478102,0.0001178161,0.0001593895,0.000365904,0.0001847407,0.0003357864,0.00033382,0.00004549051,0.000005463615],"category_scores_gemma":[0.0000160635,0.00009823524,0.0001005964,0.000538689,0.00001851097,0.001405575,0.000004399389,0.0001094553,0.00001423961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009506903,"about_ca_system_score_gemma":0.00009181201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005435241,"about_ca_topic_score_gemma":0.000001372176,"domain_scores_codex":[0.9985862,0.00003167011,0.0006206381,0.0001814893,0.0004003905,0.0001796167],"domain_scores_gemma":[0.9989772,0.0002630301,0.0001142401,0.0004533123,0.0001442843,0.00004791402],"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":[0.0000180379,0.00001017122,0.000003793023,0.0006387458,0.00006666733,4.660482e-7,0.007618749,0.7783276,0.00005687991,0.02665157,0.00001057612,0.1865967],"study_design_scores_gemma":[0.0005743357,0.00008955682,0.0000148129,0.0007390813,0.00003735335,0.00002763761,0.002190396,0.9892214,0.00150757,0.0001650308,0.005257777,0.0001750484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002511886,0.0000823142,0.9940825,0.0006229039,0.0006710633,0.0007713886,0.00002121889,0.0002108096,0.001025911],"genre_scores_gemma":[0.9643445,0.00001199401,0.03523245,0.00003554615,0.00003523369,0.0002559069,0.000009307414,0.000007517688,0.00006752444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9618326,"threshold_uncertainty_score":0.4005917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01808328787664678,"score_gpt":0.2747271749205496,"score_spread":0.2566438870439028,"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."}}