{"id":"W7126404497","doi":"10.21428/594757db.834c24c6","title":"Intra-Layer Recurrence in Transformers for Language Modeling","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Transformer; Language model; Natural language; Modeling language; Current transformer","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":[0.001132735,0.0007520331,0.0005993299,0.0005571638,0.0004224795,0.001180148,0.001296222,0.0005968477,0.004161607],"category_scores_gemma":[0.005749649,0.0005353443,0.001100639,0.0005611917,0.000796446,0.003920056,0.001108443,0.001425178,0.00129321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009152885,"about_ca_system_score_gemma":0.001008734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003727321,"about_ca_topic_score_gemma":0.009263329,"domain_scores_codex":[0.999351,0.0002400599,0.00005101488,0.0001516197,0.0001306216,0.00007584562],"domain_scores_gemma":[0.9980456,0.001143822,0.0001703798,0.000404156,0.0001773959,0.00005870127],"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":[0.0003756995,0.0001185316,0.002475042,0.0003661849,0.0001441995,0.0003495865,0.000773664,0.4943064,0.0397788,0.14875,0.004237021,0.3083249],"study_design_scores_gemma":[0.00001074417,0.00006178791,0.00009670552,0.00001177314,0.00003453463,0.00008439656,0.00003887583,0.9345878,0.01166542,0.05062227,0.002771622,0.00001408169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01627493,0.0001736263,0.9802957,0.00009363327,0.00001471488,0.00003422319,0.00007357186,0.001976,0.001063566],"genre_scores_gemma":[0.5735059,0.0004011507,0.4205508,0.000152801,0.00004142077,0.0001329861,0.0004314391,0.0009031349,0.003880344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004161607,"threshold_uncertainty_score":0.01392192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03016604409396594,"score_gpt":0.3008865339034704,"score_spread":0.2707204898095045,"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."}}