{"id":"W4411990406","doi":"10.1007/978-3-031-85747-8_4","title":"KronA: Parameter-Efficient Tuning with Kronecker Adapter","year":2025,"lang":"en","type":"book-chapter","venue":"Machine translation","topic":"Numerical Methods and Algorithms","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Kronecker delta; Adapter (computing); Computer science; Artificial intelligence; Operating system; Physics","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":[0.0002502612,0.000397888,0.0004173763,0.0002024931,0.00012082,0.0001245609,0.0004674024,0.0001779035,0.0001232166],"category_scores_gemma":[0.000007492387,0.0003097461,0.0001537627,0.0001051226,0.00005839872,0.0001277134,0.0000648303,0.0004751603,0.00004651687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004421875,"about_ca_system_score_gemma":0.00006746018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002607141,"about_ca_topic_score_gemma":0.000008574998,"domain_scores_codex":[0.998197,0.00005131093,0.000360967,0.0006781582,0.0004450661,0.0002674854],"domain_scores_gemma":[0.9988644,0.0002397532,0.0001577566,0.000576071,0.00006626063,0.00009577723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001659854,0.00002940061,0.000006570773,0.00002784489,0.0000506313,0.0000190478,0.0001246579,0.0006812643,0.00001581914,0.06494036,0.00003257384,0.9340552],"study_design_scores_gemma":[0.000808716,0.0002363385,0.00009112513,0.0003519903,0.0001038879,0.00001620376,0.000001494004,0.8110049,0.00004590048,0.0128975,0.1737148,0.0007271564],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000006684197,0.0009276444,0.834069,0.0007761172,0.0002526312,0.0002824382,0.00001747016,0.0001261661,0.1635419],"genre_scores_gemma":[0.003897186,0.00003447005,0.9205376,0.0002917065,0.0001085281,0.00001713873,0.00004987255,0.00004571037,0.07501781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9333281,"threshold_uncertainty_score":0.9999354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02634099465242189,"score_gpt":0.2579643588412323,"score_spread":0.2316233641888104,"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."}}