{"id":"W4384823501","doi":"10.1145/3539618.3591805","title":"Tevatron: An Efficient and Flexible Toolkit for Neural Retrieval","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tevatron; Computer science; Ranking (information retrieval); Pipeline (software); Flexibility (engineering); Implementation; Code (set theory); Generalization; Artificial intelligence; Information retrieval; Machine learning; Software engineering; Programming language; Large Hadron Collider; Particle physics","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":[0.0002749787,0.00006318002,0.00007235193,0.00006206184,0.00009152541,0.0001278431,0.000300175,0.00002760871,0.000006226494],"category_scores_gemma":[0.00002841175,0.00005400455,0.00002339522,0.0002402469,0.00001305115,0.0001696634,0.0001793556,0.00004046715,0.00001669284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001114764,"about_ca_system_score_gemma":0.00002103631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008734847,"about_ca_topic_score_gemma":0.000001831819,"domain_scores_codex":[0.999218,0.00001242133,0.0001066323,0.0003022477,0.0001351827,0.0002255139],"domain_scores_gemma":[0.9994993,0.00005835291,0.00001643578,0.0003223498,0.00003111535,0.00007247362],"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":[0.0000643667,0.00009519797,0.00150003,0.00008893204,0.00002082264,0.00002019863,0.002437946,0.1275278,0.006042192,0.6611227,0.004743203,0.1963367],"study_design_scores_gemma":[0.0002031864,0.00008033879,0.0008560218,0.000001909161,0.000001410318,0.000003944909,0.00002887274,0.9947277,0.001070832,0.001610319,0.001337067,0.00007836743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4641896,0.00001896745,0.5332397,0.001190143,0.0002834951,0.0001393181,8.679979e-7,0.000415754,0.0005221493],"genre_scores_gemma":[0.941415,0.000001635958,0.05583481,0.0003022943,0.0001140944,0.000006539506,0.000002119008,0.000006614582,0.00231686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8672,"threshold_uncertainty_score":0.2202242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05170918939528313,"score_gpt":0.2977516510353155,"score_spread":0.2460424616400324,"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."}}