{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07063103,0.003215183,0.004767956,0.01233209,0.004218824,0.01838767,0.008343239,0.004903221,0.01612642],"category_scores_gemma":[0.2694867,0.00180552,0.00456741,0.007153628,0.007499751,0.02987583,0.01394889,0.01350052,0.002592616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005720214,"about_ca_system_score_gemma":0.004941501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00619676,"about_ca_topic_score_gemma":0.007490536,"domain_scores_codex":[0.9257551,0.05143449,0.002543453,0.01177859,0.007177506,0.001310883],"domain_scores_gemma":[0.7259965,0.237939,0.004897822,0.02178203,0.007115759,0.00226884],"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":[0.0006624158,0.0003131073,0.01557577,0.001553779,0.001556461,0.0005083886,0.001885273,0.06337461,0.0005839083,0.6090534,0.03612681,0.2688061],"study_design_scores_gemma":[0.00005636247,0.0000853439,0.00111519,0.0004249252,0.0001029772,0.0001251174,0.0005332755,0.08747806,0.0002781254,0.8970113,0.01272327,0.00006610859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07488611,0.0360703,0.7594821,0.05890092,0.001691819,0.0003655279,0.003919008,0.004158528,0.06052567],"genre_scores_gemma":[0.5981241,0.00695478,0.3724773,0.005916322,0.001653884,0.0005338515,0.007631905,0.002817011,0.003890947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07063103,"threshold_uncertainty_score":0.3735371,"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."}}