{"id":"W3015713034","doi":"10.1007/978-3-030-45442-5_4","title":"Which BM25 Do You Mean? A Large-Scale Reproducibility Study of Scoring Variants","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reproducibility; Scale (ratio); Information retrieval; Artificial intelligence; Statistics; Mathematics; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004441281,0.0005776923,0.0009259286,0.0005469197,0.0002488671,0.0003939176,0.005107376,0.0002566864,0.00001542416],"category_scores_gemma":[0.000606276,0.0005464867,0.0001266994,0.001310458,0.0002037669,0.0006468876,0.004235153,0.00109641,0.00001683126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002275791,"about_ca_system_score_gemma":0.0006211197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006917205,"about_ca_topic_score_gemma":0.0005161946,"domain_scores_codex":[0.990797,0.0001118723,0.0009637226,0.005752212,0.001658672,0.0007165465],"domain_scores_gemma":[0.9914738,0.0002803197,0.00049676,0.006982986,0.0005394674,0.000226648],"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":[0.00005705472,0.001113836,0.009347188,0.0004543344,0.000122803,0.0002654733,0.06478319,0.2404524,0.0006577897,0.02299084,0.00002243903,0.6597326],"study_design_scores_gemma":[0.0007807019,0.0005861751,0.001315661,0.0004683236,0.00002533656,0.00003403305,0.000007303928,0.9356573,0.0007593496,0.05938894,0.0001229934,0.0008538375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006202802,0.0001861371,0.9880126,0.0006401209,0.002063493,0.0009121495,0.000005755703,0.0001905721,0.001786408],"genre_scores_gemma":[0.7660378,0.000006210821,0.2331725,0.0002591229,0.0004218318,0.000008996468,0.000001074826,0.00002870581,0.00006381718],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7598349,"threshold_uncertainty_score":0.9996986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03285745192629517,"score_gpt":0.2676645239402604,"score_spread":0.2348070720139653,"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."}}