Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.58 MCC (NT benchmark Enhancer, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Enhancer (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Enhancer', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.477 MCC (NT benchmark Enhancer Types, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Enhancer Types (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Enhancer Types', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.806 MCC (NT benchmark H3, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.605 MCC (NT benchmark H3K14ac, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K14ac (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K14ac', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.657 MCC (NT benchmark H3K36me3, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K36me3 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K36me3', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.553 MCC (NT benchmark H3K4me1, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K4me1 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K4me1', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.424 MCC (NT benchmark H3K4me2, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K4me2 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K4me2', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.512 MCC (NT benchmark H3K4me3, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K4me3 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K4me3', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.67 MCC (NT benchmark H3K79me3, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K79me3 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K79me3', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.612 MCC (NT benchmark H3K9ac, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H3K9ac (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H3K9ac', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.815 MCC (NT benchmark H4, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H4 (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H4', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.592 MCC (NT benchmark H4ac, reference fine-tuned score)unitless · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark H4ac (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'H4ac', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.962 F1 (NT benchmark Promoter All, reference fine-tuned score)fraction · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Promoter All (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Promoter All', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.962 F1 (NT benchmark Promoter Non-TATA, reference fine-tuned score)fraction · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Promoter Non-TATA (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Promoter Non-TATA', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.948 F1 (NT benchmark Promoter TATA, reference fine-tuned score)fraction · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Promoter TATA (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Promoter TATA', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.981 F1 (NT benchmark Splice Acceptor, reference fine-tuned score)fraction · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Splice Acceptor (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Splice Acceptor', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.978 F1 (NT benchmark Splice All, reference fine-tuned score)fraction · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Splice All (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Splice All', column 'GENERATOR-v2', FT value Configuration: GENERATOR-v2-1.2B, fine-tuned reference score (Datta et al. 2026) Protocol: Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1) Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026) 0.978 F1 (NT benchmark Splice Donor, reference fine-tuned score)fraction · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'
Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'
Methods, coverage and source GENERATOR-v2-1.2B on NT benchmark Splice Donor (reference fine-tuned)
gfm2-20261011-datta2026-protocol-fine-tuned-reference
Aggregation: Not reported
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Splice Donor', column 'GENERATOR-v2', FT value