{"id":"W3003420419","doi":"10.48550/arxiv.2002.00157","title":"Shared Mobile-Cloud Inference for Collaborative Intelligence","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Inference; Computer science; Cloud computing; Mobile device; Energy consumption; Curse of dimensionality; Latency (audio); Bandwidth (computing); Distributed computing; Artificial intelligence; Real-time computing; Data mining; Computer network; Telecommunications; Engineering","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":[0.00009481723,0.0003755632,0.0003889702,0.0001192046,0.0002288579,0.0001576368,0.003040968,0.0002263947,0.00001672404],"category_scores_gemma":[0.0001099495,0.000453012,0.0001711735,0.001505132,0.0001440117,0.0004577653,0.002550595,0.0005407476,0.000120648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00019252,"about_ca_system_score_gemma":0.0003552329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001029162,"about_ca_topic_score_gemma":0.00001878469,"domain_scores_codex":[0.9975409,0.00008198941,0.000274188,0.001644276,0.00009044321,0.0003681967],"domain_scores_gemma":[0.9970038,0.0005452242,0.0003695452,0.001350548,0.0004810491,0.0002498306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002817534,0.00004648863,0.00007296706,0.00005029583,0.00004044659,0.00002963012,0.0003157536,0.4186485,0.00005787566,0.5781046,0.000760134,0.001845229],"study_design_scores_gemma":[0.000155228,0.0001086902,0.00004152967,0.00005277847,0.00003151985,8.927871e-7,0.00009822766,0.6643806,0.000610007,0.3296667,0.004376749,0.0004770872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002975257,0.00009394598,0.9931013,0.0004105668,0.0004638993,0.001640216,0.0001470683,0.0004531883,0.0007145808],"genre_scores_gemma":[0.9584402,0.0002504857,0.0403554,0.0002605545,0.0001577773,0.00006668053,0.00005823833,0.00002466849,0.0003859326],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.955465,"threshold_uncertainty_score":0.9997922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1272527442954257,"score_gpt":0.2480565552715365,"score_spread":0.1208038109761108,"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."}}