{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02612723,0.002351755,0.001975358,0.00444928,0.002011767,0.004615481,0.003888383,0.003661624,0.01125755],"category_scores_gemma":[0.07712321,0.0004836155,0.001057582,0.00310084,0.003007214,0.01087749,0.005251765,0.006180594,0.006145902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00222847,"about_ca_system_score_gemma":0.001077745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004434228,"about_ca_topic_score_gemma":0.006640795,"domain_scores_codex":[0.9818334,0.009614524,0.000901074,0.002605363,0.004448348,0.0005972666],"domain_scores_gemma":[0.9750175,0.01488612,0.001112182,0.005420194,0.002780941,0.0007830029],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007188971,0.0008027356,0.01065782,0.002903195,0.003003302,0.0002733805,0.0004270255,0.05188969,0.002795865,0.05586037,0.1519574,0.7122403],"study_design_scores_gemma":[0.001074737,0.006274296,0.0240703,0.002694516,0.002300421,0.001092495,0.001357134,0.5084532,0.01151784,0.2851199,0.1556389,0.0004062651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"commentary","genre_scores_codex":[0.222302,0.4095014,0.1583567,0.04926853,0.01877152,0.0005752094,0.009082236,0.007602289,0.1245401],"genre_scores_gemma":[0.8676043,0.02090138,0.06721763,0.005389227,0.004602121,0.0003324715,0.01185681,0.001928314,0.02016776],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9738728,"threshold_uncertainty_score":0.1381757,"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."}}