{"id":"W4400909960","doi":"10.1109/icde60146.2024.00468","title":"Exploring the Space of Model Comparisons","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science; Space (punctuation)","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":[0.0002746191,0.00007028665,0.00008393384,0.00006680413,0.00007705135,0.0001567944,0.0007603159,0.00001230797,0.00001386985],"category_scores_gemma":[0.00002353849,0.00004507164,0.00005456705,0.0005073241,0.00005188272,0.0007593418,0.0002303488,0.0001055246,0.0001876316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001931872,"about_ca_system_score_gemma":0.00005975512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001445403,"about_ca_topic_score_gemma":0.00004787263,"domain_scores_codex":[0.9992399,0.00002290735,0.0001602903,0.0002022166,0.0001904424,0.0001842851],"domain_scores_gemma":[0.9992471,0.000175265,0.00001734762,0.0004783408,0.00004531672,0.00003668545],"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":[5.760481e-7,0.00001178215,0.00001008741,0.00001039023,0.000006633874,0.000003365233,0.001906649,0.02889011,0.001731469,0.955457,0.004465846,0.007506142],"study_design_scores_gemma":[0.000005529739,0.00001272169,0.00001488521,0.00001757444,0.000002226771,0.000002037222,0.0003579741,0.891637,0.09149618,0.01223436,0.004164245,0.00005525767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01562071,0.0001633147,0.9587252,0.004742793,0.0004712811,0.00007419207,4.381743e-7,0.0002226,0.01997949],"genre_scores_gemma":[0.9642354,0.00003075674,0.03412065,0.00007709693,0.00003076885,0.000017826,1.007632e-7,0.000005619101,0.001481752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9486147,"threshold_uncertainty_score":0.2411687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2854287988091037,"score_gpt":0.3272504627714538,"score_spread":0.04182166396235004,"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."}}