{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007751156,0.0002859354,0.0003731677,0.0003254768,0.0008983474,0.0008943944,0.003197854,0.0003390969,0.00002378194],"category_scores_gemma":[0.00263436,0.0001965735,0.0002272474,0.001488289,0.0002180643,0.000291863,0.002033575,0.001700898,0.00001589775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006464395,"about_ca_system_score_gemma":0.002045433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001839922,"about_ca_topic_score_gemma":0.000199388,"domain_scores_codex":[0.9929904,0.002808205,0.0006590814,0.0009392739,0.00169274,0.0009102478],"domain_scores_gemma":[0.9915777,0.004051772,0.0003471395,0.002257423,0.001648357,0.0001175861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002414396,0.0001170239,0.001117759,0.0006563624,0.0001260269,0.0000124151,0.003046091,0.8316726,0.0003676206,0.06931557,0.009043972,0.08428311],"study_design_scores_gemma":[0.0001272829,0.0005715222,0.008797643,0.002180429,0.000007339498,0.00000185292,0.0006055408,0.37516,0.02563086,0.5861062,0.0003346939,0.0004766159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03628544,0.002224221,0.9492951,0.001787885,0.0008459061,0.003189956,0.0001015501,0.0002692943,0.00600067],"genre_scores_gemma":[0.9935498,0.0001883338,0.005431199,0.00002257575,0.0002488002,0.0001096106,0.00001981522,0.00001501106,0.0004148009],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9572644,"threshold_uncertainty_score":0.8624665,"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."}}