{"id":"W4415834490","doi":"10.21203/rs.3.rs-7973071/v1","title":"The Impact of Network Preprocessing Structure Design on XAI Explanation Quality","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"QUAD Engineering (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center","keywords":"Interpretability; Preprocessor; Context (archaeology); Data pre-processing; Quality (philosophy); Key (lock); Payload (computing); Similarity (geometry)","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":[0.01404833,0.0005336931,0.0005450238,0.001359275,0.0006981309,0.003821921,0.001351708,0.001351875,0.005798671],"category_scores_gemma":[0.1870143,0.0006770493,0.0006175769,0.001037189,0.0008377727,0.006292674,0.00165851,0.00230213,0.0009041852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001599844,"about_ca_system_score_gemma":0.00192522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003006465,"about_ca_topic_score_gemma":0.003556434,"domain_scores_codex":[0.9909801,0.005405085,0.0006939201,0.001205066,0.001345068,0.0003707233],"domain_scores_gemma":[0.7199054,0.2462783,0.006970731,0.0147891,0.01094987,0.001106527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004223161,0.0009754078,0.1323417,0.001380455,0.0006156518,0.0003748212,0.002308273,0.1477102,0.03773521,0.02527757,0.006618457,0.6404393],"study_design_scores_gemma":[0.0003239779,0.000947312,0.0344497,0.0002678757,0.0007555656,0.0004003326,0.001096694,0.8604323,0.0549677,0.04178229,0.004492589,0.0000836151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6489956,0.001689026,0.3286141,0.004423769,0.0001428713,0.0003935049,0.00105252,0.003890282,0.01079829],"genre_scores_gemma":[0.9176714,0.000230498,0.07969285,0.0001623644,0.00003097266,0.0001001625,0.000681279,0.0003247946,0.001105624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01404833,"threshold_uncertainty_score":0.07429552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2119562600085777,"score_gpt":0.511208179433281,"score_spread":0.2992519194247033,"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."}}