{"id":"W3124177705","doi":"10.1609/aimag.v41i4.7383","title":"Place Your Bets: Will Machine Learning Outgrow Human Labeling?","year":2020,"lang":"en","type":"article","venue":"AI Magazine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Craft; Artificial intelligence; Computer science; Machine learning; Data science; Art; Visual arts","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003522341,0.0002515379,0.000275256,0.00009579508,0.0003396763,0.0002800484,0.00122356,0.00008378115,0.0002258283],"category_scores_gemma":[0.0003376565,0.0002524765,0.00008738071,0.000730457,0.00006392371,0.001026919,0.0005693266,0.0005549834,0.002405617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005054488,"about_ca_system_score_gemma":0.00005021371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007999819,"about_ca_topic_score_gemma":0.00007180841,"domain_scores_codex":[0.9979022,0.0001164143,0.0003984895,0.000648508,0.0003933336,0.0005410817],"domain_scores_gemma":[0.9988521,0.00008523812,0.0001317286,0.0004945181,0.0001611231,0.0002752871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001522102,0.0007318189,0.03191009,0.0003530884,0.0002683368,0.00150076,0.03039495,0.03889989,0.3117096,0.4080279,0.08552895,0.09052242],"study_design_scores_gemma":[0.0006095684,0.0009852392,0.0005421197,0.00006319125,0.00002799663,0.00003180938,0.0001968929,0.5622098,0.03384674,0.007488006,0.3930196,0.0009789952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1075124,0.001779756,0.7387246,0.1267945,0.0009070657,0.000789066,0.00001703571,0.003104078,0.02037156],"genre_scores_gemma":[0.9765444,0.00002973655,0.01012011,0.009234263,0.0003555483,0.00001394142,0.00001860252,0.00004363219,0.003639711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.869032,"threshold_uncertainty_score":0.9999927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03812501707958438,"score_gpt":0.2869459777941498,"score_spread":0.2488209607145654,"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."}}