{"id":"W4384828687","doi":"10.1145/3539618.3591902","title":"SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Compute Canada","keywords":"Computer science; Information retrieval; Benchmark (surveying); Question answering; Artificial intelligence; Weighting; Python (programming language); Language model; Machine learning","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":[0.001319974,0.0001324321,0.000153765,0.000153878,0.0003011794,0.0003366588,0.0003485594,0.00005404915,0.00002571227],"category_scores_gemma":[0.0006878462,0.0001252419,0.00005608618,0.0006388717,0.00003378565,0.0003872131,0.0002623319,0.0001363079,0.00007040727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000235795,"about_ca_system_score_gemma":0.00006895739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001239049,"about_ca_topic_score_gemma":0.000003921216,"domain_scores_codex":[0.9985417,0.00008418284,0.0002617941,0.000435478,0.0003048924,0.0003719887],"domain_scores_gemma":[0.9989008,0.000520959,0.00008542727,0.0002719857,0.00009607877,0.0001247272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002027998,0.00005073497,0.002631059,0.000168089,0.00007303611,0.00005167835,0.005586983,0.01848216,0.04177785,0.4651327,0.002270128,0.4635728],"study_design_scores_gemma":[0.0007084348,0.0001080083,0.007873773,0.00001608332,0.000007220491,0.00001224161,0.0002256548,0.983641,0.0005436631,0.00349243,0.003184363,0.0001871449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.253705,0.00004068266,0.7386654,0.001680119,0.0004362263,0.0004182181,0.000001234718,0.0007217068,0.0043314],"genre_scores_gemma":[0.9168012,0.000006944418,0.07991859,0.0005378582,0.00004747947,0.00001435778,0.000004864399,0.00001473464,0.002653992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9651588,"threshold_uncertainty_score":0.5107218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1771123195196433,"score_gpt":0.3614235738250197,"score_spread":0.1843112543053763,"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."}}