{"id":"W2999004052","doi":"10.1609/hcomp.v7i1.5274","title":"A Hybrid Approach to Identifying Unknown Unknowns of Predictive Models","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Crowdsourcing; Computer science; Task (project management); Machine learning; Set (abstract data type); Artificial intelligence; Data mining; Engineering","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":[0.000554946,0.0002500737,0.0004080065,0.000278967,0.000275342,0.0003082728,0.000831425,0.00006314128,0.000003807334],"category_scores_gemma":[0.00004605139,0.0002075955,0.0001167881,0.0004164003,0.0001121103,0.000523778,0.0005135356,0.0002484719,0.000005081024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004459666,"about_ca_system_score_gemma":0.00005393014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002828777,"about_ca_topic_score_gemma":5.550904e-7,"domain_scores_codex":[0.9980239,0.00003031972,0.0005052111,0.0006084478,0.0005256154,0.000306497],"domain_scores_gemma":[0.9984873,0.0000712737,0.0004698553,0.0002723586,0.0005798007,0.000119393],"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":[0.00007731363,0.0003140203,0.002375832,0.0008608889,0.0001124032,5.681299e-7,0.02125082,0.08310567,0.1270773,0.7548857,0.0003834302,0.009555968],"study_design_scores_gemma":[0.0006903652,0.0003023078,0.002925118,0.001002485,0.00003147712,0.00002394307,0.001066362,0.9249316,0.03642786,0.03221711,0.00002587215,0.0003554412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.797131,0.00002175737,0.1778327,0.0001383787,0.0001232302,0.0004779157,0.000002181003,0.00009113792,0.02418166],"genre_scores_gemma":[0.9917678,0.000002920156,0.00770943,0.0000983152,0.00002982548,0.00001339459,0.00000115261,0.0000197298,0.0003574003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.841826,"threshold_uncertainty_score":0.8465498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04897807387878888,"score_gpt":0.2707203747712563,"score_spread":0.2217423008924674,"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."}}