{"id":"W3034361442","doi":"10.1145/3397271.3401395","title":"A Lightweight Environment for Learning Experimental IR Research Practices","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Session (web analytics); Cloud computing; Context (archaeology); Data science; Open source; World Wide Web; Software; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0006358697,0.00006886322,0.0000709304,0.00004243099,0.0002824923,0.0002185679,0.0005468785,0.00003243778,0.0001119864],"category_scores_gemma":[0.0004378059,0.0000576464,0.00002860206,0.0001437448,0.0000267283,0.0004615296,0.0002763229,0.0002482687,0.0004027469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002869702,"about_ca_system_score_gemma":0.00002804856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000203286,"about_ca_topic_score_gemma":4.641893e-7,"domain_scores_codex":[0.9987274,0.0002005829,0.0001231369,0.0004223558,0.0003181751,0.0002083461],"domain_scores_gemma":[0.9991765,0.000313568,0.0001116389,0.0002574855,0.00002475889,0.000116051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001716121,0.0006816334,0.005408492,0.0001068394,0.00006473518,0.00001530716,0.01764696,0.0008204939,0.2628958,0.5173988,0.06044416,0.1343452],"study_design_scores_gemma":[0.0002138391,0.0003918086,0.0004175724,0.000002548477,0.000001327871,0.00000168372,0.0004385574,0.2224947,0.01649198,0.00009584745,0.7593576,0.00009253318],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007207803,0.0003057656,0.9292529,0.04918952,0.00006462609,0.0003635469,0.000001025379,0.000289883,0.01332492],"genre_scores_gemma":[0.8798661,0.00002416262,0.1174074,0.000428754,0.0001639743,0.00008957462,0.00001740694,0.000009059227,0.001993592],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8726583,"threshold_uncertainty_score":0.5176631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1884467840035469,"score_gpt":0.4048209110683452,"score_spread":0.2163741270647983,"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."}}