{"id":"W2910577570","doi":"10.1145/3308774.3308781","title":"The Neural Hype and Comparisons Against Weak Baselines","year":2019,"lang":"en","type":"article","venue":"ACM SIGIR Forum","topic":"Topic Modeling","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pace; Hyperparameter; Benchmark (surveying); Field (mathematics); Artificial intelligence; Data science; Point (geometry); Machine learning","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":[0.0001755377,0.00009670645,0.0001060981,0.00002516174,0.000190214,0.000184385,0.001044816,0.00003316687,0.00000281538],"category_scores_gemma":[0.00008807208,0.00006585007,0.00003499404,0.0000999663,0.00003177108,0.0002376709,0.0007458339,0.0001153513,0.00007089087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009007021,"about_ca_system_score_gemma":0.00001962974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001503407,"about_ca_topic_score_gemma":0.00002293332,"domain_scores_codex":[0.999103,0.00003162446,0.0001537295,0.0002579132,0.0001517574,0.0003019591],"domain_scores_gemma":[0.9986282,0.0002679198,0.00004816242,0.0009638887,0.00003240935,0.00005939345],"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":[0.00001814074,0.00005686096,0.2111689,0.00002807821,0.00004414067,0.000009035537,0.000590302,0.00310889,0.002262575,0.1451816,0.04087412,0.5966573],"study_design_scores_gemma":[0.0002733423,0.00004122083,0.005450554,0.0000100285,0.00000289337,0.000009134811,0.0001574329,0.8633653,0.0002156689,0.002807536,0.1275106,0.0001563225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8837892,0.001062334,0.08085918,0.02929353,0.0014498,0.0002632804,0.000001984538,0.0002097218,0.003071015],"genre_scores_gemma":[0.986972,0.00003242927,0.0110314,0.001127278,0.00005799068,0.000004941091,9.949856e-7,0.000006592795,0.000766366],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8602564,"threshold_uncertainty_score":0.2685288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01858451823301389,"score_gpt":0.2443701841377765,"score_spread":0.2257856659047627,"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."}}