{"id":"W4402821735","doi":"10.1101/2024.09.23.614603","title":"Protein Language Models: Is Scaling Necessary?","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Scaling; Computer science; Mathematics; Geometry","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":[0.01008311,0.001642012,0.001383715,0.0009110424,0.000836676,0.002981618,0.002844329,0.001819327,0.007804397],"category_scores_gemma":[0.07018971,0.001117597,0.001026224,0.001471539,0.001559018,0.0137328,0.003461123,0.004972818,0.005503339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001039129,"about_ca_system_score_gemma":0.001774474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005267181,"about_ca_topic_score_gemma":0.005340844,"domain_scores_codex":[0.9961869,0.001441398,0.0002561799,0.001133614,0.0007616995,0.0002202797],"domain_scores_gemma":[0.9738151,0.01338945,0.0008588508,0.008860558,0.002368995,0.0007071097],"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":[0.0008546576,0.0006352757,0.02596393,0.0008915483,0.0005034556,0.0004056951,0.001098217,0.1068776,0.008734591,0.08948755,0.1103113,0.6542363],"study_design_scores_gemma":[0.0002398109,0.0002403102,0.003381422,0.0003713476,0.0002015197,0.000352432,0.0005636364,0.5666887,0.005006237,0.3654358,0.05742377,0.00009505339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1708182,0.02159595,0.6548549,0.07494529,0.003644729,0.0006271387,0.005747275,0.02230972,0.0454569],"genre_scores_gemma":[0.6608684,0.009095579,0.299048,0.007882149,0.00259858,0.0008139726,0.007476837,0.005236216,0.006980271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01008311,"threshold_uncertainty_score":0.05332524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02002412734202891,"score_gpt":0.231310756102787,"score_spread":0.2112866287607581,"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."}}