{"id":"W4416557590","doi":"10.1007/978-3-032-07612-0_11","title":"Automatically Parallelizing Batch Inference on Deep Neural Networks Using Fiats and Fortran 2023 “Do Concurrent”","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Scalability; Inference; Leverage (statistics); Fortran; Artificial neural network; Compiler; Computation; Context (archaeology); Range (aeronautics)","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":[0.0006987611,0.0006338602,0.0006604821,0.0007658912,0.0004380551,0.0009884932,0.002288921,0.0003969604,0.000008561633],"category_scores_gemma":[0.0001401639,0.0005978806,0.0001204116,0.0007032123,0.0005033148,0.0004447202,0.001448264,0.001021505,0.000003112423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002351498,"about_ca_system_score_gemma":0.0002843615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002200716,"about_ca_topic_score_gemma":0.00002413049,"domain_scores_codex":[0.9961928,0.0000771651,0.0006930716,0.001573744,0.0007135043,0.0007497285],"domain_scores_gemma":[0.9971787,0.001044825,0.0003295299,0.001001074,0.0002406798,0.0002052362],"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":[0.000002521364,0.00001367857,0.00004680979,0.00003155428,0.000007853528,0.0000237363,0.0001491663,0.5521979,0.000003241878,0.0218516,0.000014018,0.425658],"study_design_scores_gemma":[0.0002028325,0.0001476718,0.00007260383,0.0007578374,0.00001013083,0.00002649438,1.212389e-7,0.9697856,0.00003800048,0.02828771,0.00009591648,0.0005750296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001137974,0.0007351291,0.9951221,0.0002921144,0.001238722,0.0004319264,0.000002357875,0.0004430803,0.001620742],"genre_scores_gemma":[0.3705228,0.0001447005,0.6274835,0.001488012,0.0002333958,0.000008571981,0.000006042282,0.00002787138,0.00008505816],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4250829,"threshold_uncertainty_score":0.9996473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02276136667519307,"score_gpt":0.2883862408077409,"score_spread":0.2656248741325479,"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."}}