{"id":"W4415946695","doi":"10.48550/arxiv.2506.01857","title":"Protein folding classes -- High-dimensional geometry of amino acid composition space revisited","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Council for Research in the Social Sciences, Columbia University; Eidgenössische Technische Hochschule Zürich; McGill University","keywords":"Protein folding; Folding (DSP implementation); Basis (linear algebra); Polytope; Protein structure prediction; Space (punctuation); Class (philosophy); Protein structure; Set (abstract data type)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001583455,0.0003419542,0.0004377626,0.0001481335,0.00007949045,0.00002040092,0.0003443594,0.000655812,0.00002029283],"category_scores_gemma":[0.00009851732,0.000341767,0.0002101433,0.000166495,0.00009821564,0.000004416947,0.000973652,0.000407101,0.000004987995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004272309,"about_ca_system_score_gemma":0.0001851047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005984815,"about_ca_topic_score_gemma":0.000007245562,"domain_scores_codex":[0.9983608,0.00009740442,0.0004067874,0.0006612903,0.0002139134,0.0002598338],"domain_scores_gemma":[0.9985625,0.00001505273,0.000360159,0.0007497014,0.0002436829,0.00006896629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001240232,0.00005111501,0.02381137,0.0004880922,0.0001968684,0.000006541313,0.000007775888,0.0003239501,0.9736651,0.0005412262,0.0002976057,0.0004863613],"study_design_scores_gemma":[0.0004425844,0.0001616617,0.03374603,0.000603947,0.0001039514,0.00000697138,0.000006365171,0.000136709,0.9630808,0.0006322552,0.0006852263,0.0003935358],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918965,0.002263322,0.004116414,0.0002240032,0.000289612,0.0006261753,0.0002262806,0.00003073251,0.0003269532],"genre_scores_gemma":[0.990792,0.0001230011,0.006166883,0.0001912487,0.0002780916,0.00005350158,0.001845498,0.00002535696,0.0005243808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01058431,"threshold_uncertainty_score":0.9999034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01142629685387218,"score_gpt":0.2540957782079598,"score_spread":0.2426694813540876,"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."}}