Task

Genome-wide prophage detection

Prophage detection is evaluated with grouped data partitions and explicit sequence-composition controls.

Sources

LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages

17 evaluations · 102 metric rows

At a glance

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
Property	Description and evidence
Datasets	Curated phage and bacterial reference-genome collections. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Splits	Cluster/group-aware 80:10:10 training, development and test split. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Metrics	Separate control collections assess bacterial false positives and phage false negatives. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Baselines	Genome-wide comparisons include PHASTER, geNomad, VIBRANT, Phigaro, PhiSpy and VirSorter2, plus protein-language-model-based PIDE. Embedding probes also compare pretrained and randomly initialized representations; those probes are a separate comparison from genome-wide tools. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Comparison with Traditional and Protein-based Models; embedding-probe experiment and Tables 2–3
Leakage controls	Phage clusters and bacterial genus groups are assigned wholly to one partition. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Uncertainty	Repeated experiments are summarized with mean and standard deviation for each compared model. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Entity type	Paper-specific computational evaluation protocol. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Organisms	Phage and bacterial reference collections. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Assays	Reference genome/prophage annotations. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Allowed inputs	Genomic sequence. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages
Adaptation	Supervised detection with a cluster/group-aware train/development/test split. Sources LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages

How it works

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

Evaluation methodology

Curated phage and bacterial reference-genome collections. Cluster/group-aware 80:10:10 training, development and test split. Separate control collections assess bacterial false positives and phage false negatives. Phage clusters and bacterial genus groups are assigned wholly to one partition. Repeated experiments are summarized with mean and standard deviation for each compared model.

Sources

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Protocols

Genome-wide prophage detection (Genome-wide prophage detection)

These source-backed links do not make different protocols or scores interchangeable.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies.

Comparison and metric

Genome-wide prophage detection · Table 5.

Precision (fraction) · Higher values are better for this metric.

Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.

Evaluation protocol · LAMBDA genome-wide prophage test

geNomad · Configuration · Independent external evaluation0.761
PHASTER · Configuration · Author-reported evaluation0.764
VIBRANT · Configuration · Author-reported evaluation0.728
Phigaro · Configuration · Author-reported evaluation0.839
PIDE‡ · Configuration · Author-reported evaluation0.647
EVO2 · Configuration · Independent external evaluation0.694
ProkBERT-mini† · Pipeline · Author-reported evaluation0.743
NTv2† · Pipeline · Author-reported evaluation0.756
GENERanno† · Pipeline · Author-reported evaluation0.651
megaDNA† · Pipeline · Author-reported evaluation0.627
ProkBERT-mini-long† · Pipeline · Author-reported evaluation0.654
PhiSpy · Configuration · Author-reported evaluation0.604
Caduceus† · Pipeline · Author-reported evaluation0.616
ProkBERT-mini-c† · Pipeline · Author-reported evaluation0.603
PhageBoost · Configuration · Author-reported evaluation0.468
DNABERT-2† · Pipeline · Author-reported evaluation0.492
VirSorter2 · Configuration · Author-reported evaluation0.289

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5.: Precision, Genome-wide prophage detection

Values, uncertainty and evidence

Precision: original source values
Tested entity	Printed value	Uncertainty	Evidence
geNomad · Configuration	0.761 fraction	Not reported	Independent external evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row geNomad, column Precision; XML row3 column2
PHASTER · Configuration	0.764 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PHASTER, column Precision; XML row4 column2
VIBRANT · Configuration	0.728 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row VIBRANT, column Precision; XML row5 column2
Phigaro · Configuration	0.839 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row Phigaro, column Precision; XML row6 column2
PIDE‡ · Configuration	0.647 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column Precision; XML row7 column2
EVO2 · Configuration	0.694 fraction	Not reported	Independent external evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row EVO2†, column Precision; XML row8 column2
ProkBERT-mini† · Pipeline	0.743 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini†, column Precision; XML row9 column2
NTv2† · Pipeline	0.756 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row NTv2†, column Precision; XML row10 column2
GENERanno† · Pipeline	0.651 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row GENERanno†, column Precision; XML row11 column2
megaDNA† · Pipeline	0.627 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row megaDNA†, column Precision; XML row12 column2
ProkBERT-mini-long† · Pipeline	0.654 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini-long†, column Precision; XML row13 column2
PhiSpy · Configuration	0.604 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PhiSpy, column Precision; XML row14 column2
Caduceus† · Pipeline	0.616 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row Caduceus†, column Precision; XML row15 column2
ProkBERT-mini-c† · Pipeline	0.603 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini-c†, column Precision; XML row16 column2
PhageBoost · Configuration	0.468 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PhageBoost, column Precision; XML row17 column2
DNABERT-2† · Pipeline	0.492 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row DNABERT-2†, column Precision; XML row18 column2
VirSorter2 · Configuration	0.289 fraction	Not reported	Author-reported evaluation · source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row VirSorter2, column Precision; XML row19 column2

Scope and limitations

Different tool input pipelines and training histories; †gLM and‡pLM markers retained.
Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.
No interval assigned unless printed in source cell.

Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 17 evaluations · 102 metric rows. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
EVO2: Genome-wide prophage detection Configuration: EVO2Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Independent external evaluation · Evaluation metadata: needs review
0.680 MCC Unit: unitless · Direction: higher	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models; LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5, EVO2 row, MCC column Source checking is not independent reproduction.
geNomad: Genome-wide prophage detection Configuration: geNomadProtocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Independent external evaluation · Evaluation metadata: needs review
0.794 MCC Unit: unitless · Direction: higher	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models; LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5, geNomad row, MCC column Source checking is not independent reproduction.
0.786 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row geNomad, column F1; XML row3 column6 Source checking is not independent reproduction.
VirSorter2: Genome-wide prophage detection Configuration: VirSorter2Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.046 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row VirSorter2, column FPR; XML row19 column5 Source checking is not independent reproduction.
0.289 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row VirSorter2, column Precision; XML row19 column2 Source checking is not independent reproduction.
ProkBERT-mini†: Genome-wide prophage detection Pipeline: ProkBERT-mini†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.658 MCC Unit: unitless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini†, column MCC; XML row9 column7 Source checking is not independent reproduction.
0.651 Recall Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini†, column Recall; XML row9 column3 Source checking is not independent reproduction.
megaDNA†: Genome-wide prophage detection Pipeline: megaDNA†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.595 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row megaDNA†, column F1; XML row12 column6 Source checking is not independent reproduction.
0.671 Recall Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row megaDNA†, column Recall; XML row12 column3 Source checking is not independent reproduction.
0.012 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row megaDNA†, column FPR; XML row12 column5 Source checking is not independent reproduction.
ProkBERT-mini-c†: Genome-wide prophage detection Pipeline: ProkBERT-mini-c†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.603 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini-c†, column Precision; XML row16 column2 Source checking is not independent reproduction.
0.013 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini-c†, column FPR; XML row16 column5 Source checking is not independent reproduction.
DNABERT-2†: Genome-wide prophage detection Pipeline: DNABERT-2†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.991 Specificity Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row DNABERT-2†, column Specificity; XML row18 column4 Source checking is not independent reproduction.
0.009 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row DNABERT-2†, column FPR; XML row18 column5 Source checking is not independent reproduction.
GENERanno†: Genome-wide prophage detection Pipeline: GENERanno†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.631 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row GENERanno†, column F1; XML row11 column6 Source checking is not independent reproduction.
0.651 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row GENERanno†, column Precision; XML row11 column2 Source checking is not independent reproduction.
0.648 MCC Unit: unitless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row GENERanno†, column MCC; XML row11 column7 Source checking is not independent reproduction.
PIDE‡: Genome-wide prophage detection Configuration: PIDE‡Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.984 Specificity Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column Specificity; XML row7 column4 Source checking is not independent reproduction.
0.715 MCC Unit: unitless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column MCC; XML row7 column7 Source checking is not independent reproduction.
Caduceus†: Genome-wide prophage detection Pipeline: Caduceus†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.616 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row Caduceus†, column Precision; XML row15 column2 Source checking is not independent reproduction.
0.010 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row Caduceus†, column FPR; XML row15 column5 Source checking is not independent reproduction.
ProkBERT-mini-long†: Genome-wide prophage detection Pipeline: ProkBERT-mini-long†Protocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.579 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row ProkBERT-mini-long†, column F1; XML row13 column6 Source checking is not independent reproduction.
PhageBoost: Genome-wide prophage detection Configuration: PhageBoostProtocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.034 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PhageBoost, column FPR; XML row17 column5 Source checking is not independent reproduction.
0.680 Recall Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PhageBoost, column Recall; XML row17 column3 Source checking is not independent reproduction.
PHASTER: Genome-wide prophage detection Configuration: PHASTERProtocol: Genome-wide prophage detection (Genome-wide prophage detection)Dataset: LAMBDA genome-wide prophage test Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Author-reported evaluation · Evaluation metadata: needs review
0.011 FPR Unit: fraction · Direction: lower	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedLAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PHASTER, column FPR; XML row4 column5 Source checking is not independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resource	Version	Reference
LAMBDA: A Prophage Detection Benchmark for Genomic Language Models	PMC13041943.1	Read source DOI: 10.64898/2026.03.26.714501

What is still missing

Independent batch review before import; preserve existing observation identities.

Search and extraction details

complete comparison tables extracted pending publication review

Searches

LAMBDA: A Prophage Detection Benchmark for Genomic Language Models primary paper benchmark results

Evidence locations

Table5 genome-wide versus Table3fragmentexperiment; reference construction

Strengths and limitations

Strengths and considerations

Cluster/group-aware partitioning addresses related-sequence overlap between training and testing.
Sources
LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages

Limitations and conditions

Shuffled-sequence controls test sequence-order dependence while preserving composition. Their classification scores and genome-wide localization comparisons are separate endpoints.
Sources
LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages

Profile review details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Stable record: reported-task-dd001540e0f4ec

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

18 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Input: Genomic sequence.","Evaluation: Supervised detection with a cluster/group-aware train/development/test split.","Readout: Separate control collections assess bacterial false positives and phage false negatives."] Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets Curated phage and bacterial reference-genome collections. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits Cluster/group-aware 80:10:10 training, development and test split. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised detection with a cluster/group-aware train/development/test split. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Separate control collections assess bacterial false positives and phage false negatives. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines Genome-wide comparisons include PHASTER, geNomad, VIBRANT, Phigaro, PhiSpy and VirSorter2, plus protein-language-model-based PIDE. Embedding probes also compare pretrained and randomly initialized representations; those probes are a separate comparison from genome-wide tools. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Comparison with Traditional and Protein-based Models; embedding-probe experiment and Tables 2–3 Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls Phage clusters and bacterial genus groups are assigned wholly to one partition. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty Repeated experiments are summarized with mean and standard deviation for each compared model. Individual claims	LAMBDA: A Prophage Detection Benchmark for Genomic Language Models Original source ↗ Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages Version: PMC13041943.1 Retrieved: 2026-09-16T10:33:36.240Z	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `22c2e218e87dce757907f6086a0e2ad37c13f785b34fff5bea7cfa1a6c276b16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

2 source records and release history

LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Original source · PMC13041943.1
LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Original source · PMC13041943.1

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-dd001540e0f4ec

areas: microbes-communities
tasks: Genome-wide prophage detection
entity level: task
version: Not reported
task: Genome-wide prophage detection
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
comparison panels: id: part2-lambda-prophage-2026-T5-ea2b9e053a; title: Genome-wide prophage detection · Table 5.; protocol id: paper-protocol-41c6e227215346177d; dataset id: reported-dataset-1b4f6ea24c0587; metric: Precision; unit: fraction; direction: higher; result ids: paper-result-e7a3a4d64ab390ab49; paper-result-a06603949a50933a8d; paper-result-c802c8c15e3405562c; paper-result-74849712f209d7ac30; paper-result-8e6b2821ac9808600a; paper-result-79a061473b6c519bbc; paper-result-9f8836b9f95e5299cd; paper-result-c1547589ceea1d9e54; paper-result-31813172c31b723177; paper-result-d539bf7c128bc6836a; paper-result-dad89fd9d2431eb25f; paper-result-911d0027540ad9a5d5; paper-result-181b0c4d8249ebadfe; paper-result-08e57fd4a4dfc1d04a; paper-result-85552cecec875a2a2d; paper-result-be6edcd8da058a2a18; paper-result-2532be2c98577da641; source ids: part2-lambda-prophage-2026; source locator: Table 5.: Precision, Genome-wide prophage detection; context: Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.; caveats: Different tool input pipelines and training histories; †gLM and‡pLM markers retained.; Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-lambda-prophage-2026-T5-53308364e0; title: Genome-wide prophage detection · Table 5.; protocol id: paper-protocol-41c6e227215346177d; dataset id: reported-dataset-1b4f6ea24c0587; metric: Recall; unit: fraction; direction: higher; result ids: paper-result-97e52289280e1fae96; paper-result-cdb7fa6252004e69a0; paper-result-d2671f470add052c95; paper-result-b055c366896ed5de0f; paper-result-a6a13a958788577c38; paper-result-f115eb38187794e35f; paper-result-44f9400644e72d0d06; paper-result-b1d0506bc82f67b1eb; paper-result-497e6cae9ab0ad3020; paper-result-296e3f408bd35593be; paper-result-df8cde861fc3b93615; paper-result-8ae7ec3f68a41210d2; paper-result-62f561dad5ccb58842; paper-result-6da890addbc1047a27; paper-result-40524c22a54dc0a9ea; paper-result-86d4ac1a8cf79fcb61; paper-result-b507c4759c12caf2ff; source ids: part2-lambda-prophage-2026; source locator: Table 5.: Recall, Genome-wide prophage detection; context: Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.; caveats: Different tool input pipelines and training histories; †gLM and‡pLM markers retained.; Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-lambda-prophage-2026-T5-5384a9619c; title: Genome-wide prophage detection · Table 5.; protocol id: paper-protocol-41c6e227215346177d; dataset id: reported-dataset-1b4f6ea24c0587; metric: Specificity; unit: fraction; direction: higher; result ids: paper-result-e14d406e39fc25afe5; paper-result-b6f96d58c259c3ddbc; paper-result-c0332beda4d25cf031; paper-result-998cbe6bfc62cf0dc2; paper-result-11b156230bc9c72f52; paper-result-e529fb96fa1afd802f; paper-result-e8ad7325a802539ff7; paper-result-4fca80021785b3b17d; paper-result-9759b1c8ba49d0637c; paper-result-ad193cda382dc5f155; paper-result-c9c3c03da0764cd397; paper-result-dfc1dd7998a8f0b87f; paper-result-c42e3020111d6d6d92; paper-result-bfb95eb33658a02228; paper-result-9f218b36b330581b4e; paper-result-0db65312a74302c448; paper-result-edcf8c457f3b726d0c; source ids: part2-lambda-prophage-2026; source locator: Table 5.: Specificity, Genome-wide prophage detection; context: Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.; caveats: Different tool input pipelines and training histories; †gLM and‡pLM markers retained.; Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-lambda-prophage-2026-T5-906d46edf7; title: Genome-wide prophage detection · Table 5.; protocol id: paper-protocol-41c6e227215346177d; dataset id: reported-dataset-1b4f6ea24c0587; metric: FPR; unit: fraction; direction: lower; result ids: paper-result-64d71695f6ecff7d37; paper-result-394b7604923b5adc9e; paper-result-4817f5ddcd632a2f5a; paper-result-f28d464414ab011128; paper-result-dcef5aaee3067608f0; paper-result-4f8c584360869901f5; paper-result-87215da087c0b15cfa; paper-result-d8f68c1b918eed398d; paper-result-7d20b1be5cc6e8043a; paper-result-33209fc0bc77878645; paper-result-f46c39cbbb69ebaf6d; paper-result-dc81699af30d77270d; paper-result-36e647332f530a2641; paper-result-114205a0aa30717ddd; paper-result-23456ae224ed60c7f6; paper-result-1a8de38949de72ecf2; paper-result-0261b022358700df1f; source ids: part2-lambda-prophage-2026; source locator: Table 5.: FPR, Genome-wide prophage detection; context: Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.; caveats: Different tool input pipelines and training histories; †gLM and‡pLM markers retained.; Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-lambda-prophage-2026-T5-1f80d97aab; title: Genome-wide prophage detection · Table 5.; protocol id: paper-protocol-41c6e227215346177d; dataset id: reported-dataset-1b4f6ea24c0587; metric: F1; unit: fraction; direction: higher; result ids: paper-result-2c8d80c884705f8507; paper-result-efe194ad9f2e77e0cd; paper-result-cbd98a692f3688820b; paper-result-80b1d1f3626c4fdd21; paper-result-66bb9bf85666106228; paper-result-d42a3d827c6a3e8fbf; paper-result-d06ddd98d6567adf47; paper-result-b19996145b265cbe13; paper-result-0f2fe445b92f4f28de; paper-result-06e7cc4727bad189fe; paper-result-1bb7a28861bb8e5821; paper-result-aeb146019fa85bcdf2; paper-result-b133e6df703f7611a7; paper-result-5db8cdaca7588fa5ca; paper-result-6ce4c22c1bee5109ba; paper-result-81f827e7549c692370; paper-result-84ce8d28189999f1bd; source ids: part2-lambda-prophage-2026; source locator: Table 5.: F1, Genome-wide prophage detection; context: Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.; caveats: Different tool input pipelines and training histories; †gLM and‡pLM markers retained.; Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-lambda-prophage-2026-T5-27d631c420; title: Genome-wide prophage detection · Table 5.; protocol id: paper-protocol-41c6e227215346177d; dataset id: reported-dataset-1b4f6ea24c0587; metric: MCC; unit: unitless; direction: higher; result ids: lit-038; paper-result-ad8f7a939fe6fedda9; paper-result-a65058240bc1b8e345; paper-result-4615d60b969151525b; paper-result-1fb211666087dddc72; lit-037; paper-result-02e0fc1798b036d3d3; paper-result-ffa067657fc300a3b6; paper-result-44767fd81dbbcd9a15; paper-result-b7a2e1cb2f2c95a963; paper-result-5f92e457e48dca6143; paper-result-6104a0c48f501a442a; paper-result-dcde4b7b93eec8e1ce; paper-result-6ac04b40baae819886; paper-result-dae3fa85e4aea76696; paper-result-9e2cfcc5dcc55abc03; paper-result-b903ac601cf415526f; source ids: part2-lambda-prophage-2026; source locator: Table 5.: MCC, Genome-wide prophage detection; context: Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations.; caveats: Different tool input pipelines and training histories; †gLM and‡pLM markers retained.; Table5 reports point estimates; ten repeats belong to separate Table3 fragment experiment.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17
benchmark research: review date: 2026-09-17; status: complete_comparison_tables_extracted_pending_publication_review; primary sources: part2-lambda-prophage-2026; inspected locators: Table5 genome-wide versus Table3fragmentexperiment; reference construction; searched queries: LAMBDA: A Prophage Detection Benchmark for Genomic Language Models primary paper benchmark results; gaps: Independent batch review before import; preserve existing observation identities.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata: protocol version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: lambda-prophage-2026; source locator: Methods: LAMBDA Benchmark Dataset Construction; Data Splitting and Data Leakage Prevention; control datasets; cached text lines 66–67, 78–85; uncertainty/repeat-run/statistical-comparison passages; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: LAMBDA genome-wide prophage test
evaluates task: Genome-wide prophage detection (Genome-wide prophage detection)

Suggest a correction