Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Downstream of Transcript variants, at least one review star 0.97 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Downstream of Transcript)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Downstream of Transcript variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Downstream of Transcript', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Intronic variants, at least one review star 0.95 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Intronic)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Intronic variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Intronic', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Missense variants, at least one review star 0.84 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Missense)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Missense variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Missense', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Noncoding variants, at least one review star 0.94 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Noncoding)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Noncoding variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Noncoding', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Splice Acceptor variants, at least one review star 0.82 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Splice Acceptor)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Splice Acceptor variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Splice Acceptor', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Splice Donor variants, at least one review star 0.83 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Splice Donor)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Splice Donor variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Splice Donor', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Start Codon variants, at least one review star 0.77 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Start Codon)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Start Codon variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Start Codon', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Stop Lost variants, at least one review star 0.81 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Stop Lost)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Stop Lost variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Stop Lost', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Synonymous variants, at least one review star 0.85 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Synonymous)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Synonymous variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Synonymous', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar Upstream of Transcript variants, at least one review star 0.74 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Upstream of Transcript)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar Upstream of Transcript variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row 'Upstream of Transcript', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar 3’ UTR variants, at least one review star 0.94 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class 3’ UTR)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar 3’ UTR variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row '3’ UTR', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Protocol: ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class Dataset subset: ClinVar 5’ UTR variants, at least one review star 0.94 AUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class 5’ UTR)unitless · higher
Uncertainty: Not reported by the source: Table 1 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on ClinVar 5’ UTR variants, likelihood-ratio scoring
phylogpn-20261116-protocol-clinvar-llr-auroc
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 1, row '5’ UTR', column 'PhyloGPN' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND CHROMATIN: Chromatin accessibility Dataset subset: ENCODE chromatin accessibility (BEND split) 0.86 AUROC (BEND Chromatin Accessibility, two-layer CNN trained on frozen embeddings)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND Chromatin Accessibility
bend-task-chromatin
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'Chromatin Accessibility (AUROC)' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND CPG: CpG methylation Dataset subset: ENCODE CpG methylation (BEND split) 0.94 AUROC (BEND CpG Methylation, two-layer CNN trained on frozen embeddings)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND CpG Methylation
bend-task-cpg
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'CpG Methylation (AUROC)' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND VARIANT-DISEASE: Noncoding variant effects on disease Dataset subset: ClinVar disease variants (BEND split) 0.96 AUROC (BEND Disease VEP, cosine distance between the embeddings of the reference and alternative sequences)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND Disease VEP
bend-task-variant-disease
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'Disease VEP (AUROC)' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND ENHANCER: Enhancer annotation Dataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split) 0.04 AUPRC (BEND Enhancer Annotation, two-layer CNN trained on frozen embeddings)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND Enhancer Annotation
bend-task-enhancer
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'Enhancer Annotation (AUPRC)' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND VARIANT-EXPRESSION: Noncoding variant effects on expression Dataset subset: DeepSEA expression variants (BEND split) 0.50* AUROC (BEND Expression VEP, cosine distance between the embeddings of the reference and alternative sequences)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND Expression VEP
bend-task-variant-expression
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'Expression VEP (AUROC)' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) 0.50* MCC (BEND Gene Finding, two-layer CNN trained on frozen embeddings)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND Gene Finding
bend-task-gene-finding
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'Gene Finding (MCC)' Configuration: PhyloGPN (481 bp receptive field, about 83M parameters) Task: BEND HISTONE: Histone modification Dataset subset: ENCODE histone modification (BEND split) 0.8 AUROC (BEND Histone Modification, two-layer CNN trained on frozen embeddings)unitless · higher
Uncertainty: Not reported by the source: Table 2 prints no interval or spread.
Coverage: Not reported scored / Not reported eligible
Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Methods, coverage and source PhyloGPN on BEND Histone Modification
bend-task-histone
Aggregation: Not reported
A Phylogenetic Approach to Genomic Language Modeling · Table 2, row 'PhyloGPN', column 'Histone Modification (AUROC)'