{"id":"W7125769103","doi":"10.21428/594757db.516b1ccb","title":"Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach","year":2025,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Forgetting; Robustness (evolution); Adaptability; Recall; Quality (philosophy); Selection (genetic algorithm); Incremental learning","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":[0.001300026,0.0009022047,0.0007883726,0.0005526569,0.0002645845,0.0007459863,0.002015044,0.000718912,0.001258272],"category_scores_gemma":[0.004055697,0.0003339295,0.0005404009,0.0003384404,0.0005376637,0.001654822,0.001521437,0.0009598712,0.0005786708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004879813,"about_ca_system_score_gemma":0.001037551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002923343,"about_ca_topic_score_gemma":0.003636009,"domain_scores_codex":[0.9996425,0.00009075826,0.00002678856,0.0001167068,0.00008786774,0.00003538998],"domain_scores_gemma":[0.9985248,0.0006624236,0.0001427747,0.0002948984,0.0002782707,0.0000968807],"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":[0.0007488336,0.0006412111,0.004287937,0.0002642196,0.0001899649,0.000222458,0.0005120937,0.3342024,0.03764041,0.00438182,0.001772323,0.6151364],"study_design_scores_gemma":[0.00001927576,0.0002240342,0.0003632404,0.000008884088,0.00003198136,0.00006844613,0.00003186974,0.9845338,0.01201547,0.001979072,0.0007071407,0.00001671102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1123211,0.0005342897,0.8816435,0.0001596444,0.00005909981,0.00007315558,0.00005304275,0.00381105,0.001345038],"genre_scores_gemma":[0.78979,0.0002999793,0.2064487,0.000221377,0.00003201223,0.000117618,0.0001544255,0.000176824,0.002759057],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002923343,"threshold_uncertainty_score":0.006875277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007261221894014275,"score_gpt":0.2187904393358591,"score_spread":0.2115292174418448,"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."}}