{"id":"W4409365759","doi":"10.1609/aaai.v39i9.33059","title":"Efficient Neural Network Encoding for 3D Color Lookup Tables","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto; Vector Institute","funders":"Samsung","keywords":"Lookup table; Computer science; Encoding (memory); Artificial neural network; Artificial intelligence; Programming language","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":[0.0002012846,0.0003673198,0.0002786004,0.0003162544,0.0002142509,0.0006097801,0.0008800538,0.0004266611,0.003916471],"category_scores_gemma":[0.001223283,0.0001846946,0.0002323073,0.0004742536,0.0002799848,0.001076825,0.0005073756,0.0006423001,0.0006374248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000661022,"about_ca_system_score_gemma":0.0005389487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004193348,"about_ca_topic_score_gemma":0.006507376,"domain_scores_codex":[0.9998763,0.00002053361,0.000008683689,0.00002526873,0.00004851634,0.00002067594],"domain_scores_gemma":[0.9997119,0.0001015446,0.00002391993,0.00005474871,0.00009619352,0.0000116251],"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":[0.0002757176,0.0001147756,0.0007554221,0.0001982155,0.00003831161,0.0001911991,0.0001079038,0.5189304,0.04868918,0.04641017,0.007050789,0.3772379],"study_design_scores_gemma":[0.00000692753,0.00001873075,0.00009178559,0.00000733157,0.000005218583,0.0000272522,0.000007933383,0.9857964,0.007179868,0.005365368,0.001486597,0.000006546381],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07432413,0.0004098917,0.9125675,0.0003304055,0.0001541566,0.00005134645,0.0004135545,0.002596247,0.009152631],"genre_scores_gemma":[0.7323503,0.0003212776,0.2591485,0.0001517047,0.00003718825,0.0001126205,0.0005891553,0.0001557653,0.007133521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004193348,"threshold_uncertainty_score":0.01310188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05474742245764885,"score_gpt":0.3205700956536051,"score_spread":0.2658226731959562,"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."}}