{"id":"W7126423241","doi":"10.21428/594757db.269457de","title":"GCE: Confidence Calibration Error for ImprovedTrustworthiness of Graph Neural Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Graph; Artificial neural network; Confidence interval; Calibration; Homogeneous; Pattern recognition (psychology); Code (set theory); Training set; Error function","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":[0.0001872877,0.0001810661,0.0002067933,0.0001248999,0.00007959886,0.000164076,0.0006489923,0.00009531632,0.000009700369],"category_scores_gemma":[0.00002599894,0.0001468527,0.0001594835,0.0009566803,0.00008442389,0.001234344,0.0001424391,0.0001795547,9.165791e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001095264,"about_ca_system_score_gemma":0.00003375242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001673623,"about_ca_topic_score_gemma":0.00002656529,"domain_scores_codex":[0.9985716,0.00003180003,0.0003632667,0.0005051862,0.0001927572,0.0003354037],"domain_scores_gemma":[0.9989095,0.0003499332,0.00008673727,0.0004571361,0.0001116457,0.00008500089],"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":[0.00002824169,0.00002464026,0.0001674381,0.0001168606,0.00003156813,0.00001514431,0.0001259142,0.1794905,0.001301402,0.7409091,0.002819794,0.07496935],"study_design_scores_gemma":[0.0001300048,0.0001046087,0.0001123248,0.00003233194,0.000008740957,0.00001371723,0.00000772462,0.9660096,0.00108079,0.03202791,0.0003029039,0.0001693088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002762721,0.0009181991,0.9925809,0.0009823951,0.001742502,0.0004387957,0.000003942883,0.0004579262,0.0001126312],"genre_scores_gemma":[0.9670364,0.00002550308,0.03197599,0.0004135405,0.0001700086,0.00006345626,0.000008191088,0.00001907253,0.0002878673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9642736,"threshold_uncertainty_score":0.5988478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01637108806119735,"score_gpt":0.2768592316950903,"score_spread":0.2604881436338929,"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."}}