{"id":"W2972715831","doi":"10.1016/j.neucom.2019.08.082","title":"Finding decision jumps in text classification","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Jumper; Machine learning; Benchmark (surveying); Process (computing); Artificial neural network; Feature (linguistics); Reinforcement learning; Key (lock); Reading (process)","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":[0.000341079,0.00009378255,0.0001164728,0.0001835018,0.00005846107,0.0001191003,0.00063159,0.00004771938,0.00000793154],"category_scores_gemma":[0.00005917392,0.00009704636,0.0000340733,0.0004141444,0.000004965217,0.0003001718,0.0002980176,0.0002018696,0.0002317179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004856987,"about_ca_system_score_gemma":0.0000270814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001018006,"about_ca_topic_score_gemma":0.000002030183,"domain_scores_codex":[0.9987107,0.00004953532,0.00027915,0.0004803586,0.0002246963,0.0002555391],"domain_scores_gemma":[0.9991108,0.0002608688,0.00008778509,0.0004762147,0.0000250205,0.00003930637],"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":[0.000003931262,0.00004056889,0.07716271,0.00002171072,0.000001773472,0.00002118155,0.0008009752,0.03657264,0.01165223,0.03047256,0.0000796124,0.8431701],"study_design_scores_gemma":[0.0002168519,0.00001404694,0.07358849,0.00005359127,3.959523e-7,0.00001067135,0.000014975,0.9240584,0.0002309789,0.001030761,0.0006851618,0.00009562327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5940579,0.00001126271,0.402996,0.000165367,0.0004067291,0.0001104594,3.507642e-8,0.00008923835,0.002163073],"genre_scores_gemma":[0.943703,0.000001208482,0.05597014,0.000199644,0.00006068741,0.000002070475,3.161666e-7,0.000007953474,0.00005496838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8874858,"threshold_uncertainty_score":0.3957436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03601712965880887,"score_gpt":0.2772204695566182,"score_spread":0.2412033398978093,"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."}}