{"id":"W2946245775","doi":"10.65109/yaad6137","title":"Contradict the Machine: A Hybrid Approach to Identifying Unknown Unknowns","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Crowdsourcing; Set (abstract data type); Machine learning; Artificial intelligence; Data mining; State (computer science); Algorithm","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":[0.0005879019,0.0001753216,0.0001845506,0.0001132098,0.0001114209,0.0004712527,0.002961618,0.00002992327,0.00004033064],"category_scores_gemma":[0.00005104966,0.0001118785,0.00007016033,0.000419036,0.00003428093,0.0005165776,0.0009518379,0.0001810031,0.000576777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004151676,"about_ca_system_score_gemma":0.00004532029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001704935,"about_ca_topic_score_gemma":0.00000919275,"domain_scores_codex":[0.9984489,0.00007855724,0.0002221342,0.0005457943,0.0003389226,0.0003656793],"domain_scores_gemma":[0.9979728,0.0001292721,0.00005987147,0.001681813,0.00004554333,0.0001106995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008386954,0.0001466955,0.001470138,0.0000299812,0.00005779552,0.00001250078,0.0009018765,0.00004139768,0.002120933,0.8548772,0.07341554,0.06691752],"study_design_scores_gemma":[0.001488843,0.0005616689,0.01434497,0.0001715917,0.00004969951,0.0005801012,0.0001688479,0.4364377,0.04525163,0.02319517,0.4757856,0.001964241],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01052897,0.00005518419,0.8667622,0.0009832345,0.0002742159,0.0005601461,0.00001032159,0.0009064371,0.1199193],"genre_scores_gemma":[0.7740934,0.000004831549,0.2217004,0.001267767,0.00003788924,0.00004906551,0.000008878275,0.00001468234,0.002823105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8316821,"threshold_uncertainty_score":0.7413493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01802494940759993,"score_gpt":0.2482879605193553,"score_spread":0.2302630111117554,"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."}}