{"id":"W7130548454","doi":"10.1109/ictc66702.2025.11388563","title":"Enhancing Lightweight IRSR Models via Knowledge Distillation with Structural and Spectral Losses","year":2025,"lang":"","type":"article","venue":"","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Distillation; Key (lock); Range (aeronautics); Enhanced Data Rates for GSM Evolution; Image (mathematics); Data modeling; Domain (mathematical analysis)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002988724,0.0005357892,0.000545339,0.0004160099,0.0003516797,0.0002271723,0.0001625058,0.0002915513,0.0002778206],"category_scores_gemma":[0.0001049117,0.0004497769,0.0000833294,0.0006976805,0.0001692881,0.0007700066,0.0001169845,0.0004675808,0.00001607393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002750191,"about_ca_system_score_gemma":0.00009447438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004207642,"about_ca_topic_score_gemma":0.0002025707,"domain_scores_codex":[0.9979034,0.0001578464,0.0005820768,0.0005842799,0.0001738913,0.0005984959],"domain_scores_gemma":[0.9987557,0.0004991454,0.00008569729,0.0003782409,0.0001699481,0.0001113015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007913199,0.00006499368,0.004725604,0.004188248,0.001725852,0.00005419434,0.009077351,0.5337392,0.2225313,0.1515938,0.0003249228,0.07118328],"study_design_scores_gemma":[0.0005633945,0.0001221303,0.00487506,0.0002135079,0.000144138,0.00003933275,0.0003763931,0.4744886,0.4832597,0.03512057,0.0002141661,0.0005830635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3554532,0.00296694,0.6119964,0.0000623442,0.001195458,0.000313949,0.000006590375,0.0004099382,0.02759516],"genre_scores_gemma":[0.8086135,0.0001723578,0.1886794,0.00001394714,0.0002047928,0.00001312033,0.000004594441,0.00004245364,0.002255796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4531603,"threshold_uncertainty_score":0.9997954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646007692318635,"score_gpt":0.2599523342715061,"score_spread":0.2434922573483198,"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."}}