{"id":"W2935885634","doi":"10.1145/3331184.3331296","title":"An Axiomatic Approach to Regularizing Neural Ranking Models","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Axiom; Axiomatic system; Ranking (information retrieval); Regularization (linguistics); Machine learning; Computer science; Generalization; Artificial neural network; Artificial intelligence; Relevance (law); Convergence (economics); Training set; Set (abstract data type); Mathematical optimization; Algorithm; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006222989,0.0003390102,0.0004475629,0.0002585301,0.00008656374,0.000800316,0.003376561,0.0002455316,0.000003172062],"category_scores_gemma":[0.0000137654,0.0003176438,0.0001356165,0.0001903358,0.00001102454,0.0006975261,0.002827133,0.0004875861,0.00003079494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009180691,"about_ca_system_score_gemma":0.0001214881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001706154,"about_ca_topic_score_gemma":0.00000287533,"domain_scores_codex":[0.9970548,0.000130366,0.0004549183,0.001336786,0.0005580755,0.0004650474],"domain_scores_gemma":[0.9964268,0.00003464592,0.0001358031,0.003129392,0.00008660321,0.0001867261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001080729,0.00002997845,0.00001256919,0.0001127066,0.00001172406,0.000001744036,0.001751263,0.8692111,0.0001209768,0.1177538,0.00002890827,0.01096411],"study_design_scores_gemma":[0.0001053957,0.00001498306,0.00002959569,0.00007395029,0.000007550305,0.00001118557,0.00003459652,0.9573126,0.0000788977,0.04193709,0.00001047067,0.0003836849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02258794,0.00005830514,0.9505677,0.0003551132,0.0009192196,0.0007253923,8.359465e-7,0.0005880804,0.02419738],"genre_scores_gemma":[0.5359182,6.471363e-7,0.4632464,0.0004291216,0.00009380175,0.00003166162,0.000004953542,0.00001748701,0.0002577586],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5133302,"threshold_uncertainty_score":0.9999276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06637320565648477,"score_gpt":0.2703737946978024,"score_spread":0.2040005890413176,"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."}}