{"id":"W4416020257","doi":"10.1016/j.procs.2025.10.130","title":"LiteDHAZE: An Adversarial Dehazing Network for Robust Robotic Perception in Challenging Visual Conditions","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Adversarial system; Low latency (capital markets); Perception; Encoding (memory); Perspective (graphical); Feature (linguistics); Latency (audio); Generative adversarial network; Object (grammar); Robot","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":[0.001206941,0.0001971781,0.0002095831,0.0005913332,0.0005532982,0.0005660535,0.001587661,0.00006843222,0.000002950557],"category_scores_gemma":[0.00007905856,0.0002145462,0.00005172841,0.002253957,0.0002015336,0.002867718,0.0005554195,0.0001601713,0.000004936372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002577001,"about_ca_system_score_gemma":0.000370952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000112757,"about_ca_topic_score_gemma":0.00002143751,"domain_scores_codex":[0.9976241,0.00004667691,0.0003495155,0.0009111058,0.0003535611,0.0007150308],"domain_scores_gemma":[0.9989802,0.000118647,0.00009513668,0.0004288824,0.0002743437,0.0001028146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004373704,0.0008512164,0.004468842,0.0003214761,0.00002620713,0.00002257634,0.006060086,0.3873438,0.0168662,0.2073943,0.00356788,0.3730337],"study_design_scores_gemma":[0.0003354745,0.0001569705,0.007046432,0.0001667435,0.000004748546,0.000004948085,0.00002378622,0.9863914,0.0007139337,0.004848627,0.00007874163,0.0002282226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009452279,0.00004031238,0.9870084,0.0005868926,0.001500094,0.0006965638,6.762272e-7,0.0005322056,0.0001825659],"genre_scores_gemma":[0.4893735,0.000007160339,0.5098335,0.0003963805,0.0002470418,0.0001147127,0.000004926035,0.000006091916,0.00001677903],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5990475,"threshold_uncertainty_score":0.8748939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01676636026257652,"score_gpt":0.3066416635815305,"score_spread":0.289875303318954,"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."}}