{"id":"W4400528755","doi":"10.1145/3626772.3657861","title":"Systematic Evaluation of Neural Retrieval Models on the Touché 2020 Argument Retrieval Subset of BEIR","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; European Commission; HORIZON EUROPE Framework Programme; Compute Canada","keywords":"Argument (complex analysis); Computer science; Artificial intelligence; Information retrieval; Natural language processing; Biology","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":[0.01590022,0.002663607,0.002213035,0.002722945,0.0007009592,0.00221315,0.002696373,0.002863179,0.003737758],"category_scores_gemma":[0.04088029,0.0006451537,0.00155772,0.001553577,0.001161641,0.00408636,0.002260303,0.003180422,0.003033357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001780596,"about_ca_system_score_gemma":0.00115508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00602784,"about_ca_topic_score_gemma":0.00717448,"domain_scores_codex":[0.990826,0.004862548,0.0007847175,0.001576534,0.001635893,0.0003143491],"domain_scores_gemma":[0.9757356,0.0168661,0.0007707701,0.003561545,0.002469253,0.0005967069],"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":[0.01014427,0.003710014,0.01082507,0.007517728,0.002760042,0.0006513653,0.001079392,0.2085811,0.04013593,0.003175547,0.06118714,0.6502324],"study_design_scores_gemma":[0.001082718,0.004870037,0.01819325,0.0004847709,0.0007048422,0.0005378682,0.0007985587,0.9170085,0.03863654,0.003998292,0.01343571,0.0002488519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8476397,0.02548136,0.07385205,0.002184821,0.001161343,0.001601359,0.009755164,0.01659148,0.02173266],"genre_scores_gemma":[0.8677399,0.002138684,0.08649781,0.001052956,0.0003235606,0.0007865477,0.03348667,0.001001775,0.006972145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01590022,"threshold_uncertainty_score":0.08408946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06782064987352145,"score_gpt":0.29225979395797,"score_spread":0.2244391440844485,"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."}}