{"id":"W6910483583","doi":"10.48448/kkrt-xr15","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Swift; Inference; Set (abstract data type); Joint (building); Computation; Architecture; Code (set theory)","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":[0.001450251,0.00153328,0.00100316,0.000834998,0.000566711,0.001645096,0.002553651,0.001171555,0.005890483],"category_scores_gemma":[0.005303283,0.001039773,0.001228579,0.000648605,0.0008093363,0.004662075,0.002747457,0.002815772,0.003178719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008226572,"about_ca_system_score_gemma":0.001595999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00566281,"about_ca_topic_score_gemma":0.01560649,"domain_scores_codex":[0.9990333,0.0002670287,0.00004867771,0.0002666279,0.0002697842,0.0001145913],"domain_scores_gemma":[0.9983569,0.0006763112,0.00009747425,0.0005624818,0.0002238311,0.00008297816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006833021,0.0003253826,0.002726477,0.0002453535,0.0002702216,0.0004887957,0.0003582047,0.3720526,0.02193302,0.03785831,0.01847915,0.5445791],"study_design_scores_gemma":[0.00002049089,0.00003228801,0.0001220264,0.000007930052,0.00001747816,0.00004115562,0.00002552436,0.9739655,0.005456239,0.01819713,0.002099303,0.00001489442],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01775494,0.000251441,0.9638193,0.0002772604,0.0000859315,0.00005545008,0.0004896556,0.01466702,0.002598947],"genre_scores_gemma":[0.4083116,0.0003017171,0.5749661,0.0005523441,0.0001253953,0.0001773489,0.004023633,0.002721398,0.008820497],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.005890483,"threshold_uncertainty_score":0.01970565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0312230310759621,"score_gpt":0.267455505177619,"score_spread":0.2362324741016569,"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."}}