{"id":"W4416478222","doi":"10.1145/3680207.3765592","title":"Demo: Split-and-Pipeline: Collaborative Large Model Inference on Edge Devices","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Testbed; Inference; Enhanced Data Rates for GSM Evolution; Scheme (mathematics); Edge device; Throughput; Data transmission; Edge computing","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":[0.001395595,0.00177426,0.000984181,0.0005286396,0.0008173711,0.001190932,0.003454423,0.001482535,0.01300696],"category_scores_gemma":[0.005281995,0.000976837,0.0009872119,0.0006108962,0.001013625,0.003162296,0.002840672,0.002861188,0.002183215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008679682,"about_ca_system_score_gemma":0.001848618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01704928,"about_ca_topic_score_gemma":0.04233137,"domain_scores_codex":[0.9993572,0.0001475877,0.00003029604,0.0002112715,0.0001577202,0.00009602137],"domain_scores_gemma":[0.9984865,0.0006176176,0.00004040036,0.0005928501,0.0001342663,0.0001283108],"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":[0.001905314,0.0005332349,0.004620136,0.0004903871,0.0004931055,0.0008841127,0.0004519726,0.5983425,0.01765869,0.02484442,0.1323253,0.2174509],"study_design_scores_gemma":[0.00009143382,0.0000298046,0.0001691742,0.000006446792,0.00001138305,0.00003668624,0.00002859509,0.9853637,0.002879489,0.008071562,0.003298327,0.00001343652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03494256,0.000552878,0.8845089,0.001132489,0.0002897074,0.0003152945,0.002913462,0.06708694,0.008257831],"genre_scores_gemma":[0.4018964,0.0003044563,0.5816069,0.0007752813,0.00007542547,0.0003915422,0.006036691,0.00289745,0.006015903],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01704928,"threshold_uncertainty_score":0.04351258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02126014214548735,"score_gpt":0.3278883683632451,"score_spread":0.3066282262177578,"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."}}