{"id":"W4386870537","doi":"10.1007/978-981-99-6207-5_21","title":"Adder Encoder for Pre-trained Language Model","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Adder; Benchmark (surveying); Transformer; Encoder; Efficient energy use; Energy consumption; Language model; Computer engineering; Artificial intelligence; Electrical 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":[0.0009253746,0.0005163667,0.0005091298,0.0006995786,0.0002234828,0.0004407142,0.003723897,0.0003663923,0.000009195564],"category_scores_gemma":[0.0001559958,0.0004786316,0.0001948751,0.0004199065,0.0002770161,0.0005121485,0.001316648,0.0005821759,0.00003496258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001924107,"about_ca_system_score_gemma":0.0006531451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001743843,"about_ca_topic_score_gemma":0.00009683862,"domain_scores_codex":[0.9958839,0.0000168212,0.0005262034,0.001844656,0.0008963174,0.0008320367],"domain_scores_gemma":[0.9971282,0.0005358912,0.0002055795,0.001743591,0.0002139798,0.0001727316],"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":[0.000005270505,0.00001408134,0.000002957192,0.00006710987,0.00001262229,0.00003450367,0.003260057,0.5585279,0.0002451312,0.05040427,0.00007937426,0.3873467],"study_design_scores_gemma":[0.0002153748,0.0000505339,0.000004994667,0.0001547857,0.000005821398,0.00001147963,2.435176e-7,0.7896709,0.0003477811,0.2089565,0.0001460755,0.0004354868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005248746,0.000161364,0.9943613,0.0009017786,0.001548345,0.0007038899,0.00001847325,0.0004865885,0.001765734],"genre_scores_gemma":[0.03352448,0.00001534621,0.9577221,0.001881414,0.0006971239,0.00005601867,0.00001130714,0.00007785378,0.006014351],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3869112,"threshold_uncertainty_score":0.9997665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02969817206388813,"score_gpt":0.283785682589629,"score_spread":0.2540875105257409,"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."}}