Dataset

ProteinNet CASP12

Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

Evaluation results

Release 2026-09-17-d277315f7d76 · 10 evaluations · 10 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
TAPE ResNet: ProteinNet CASP12 Model: TAPE ResNetTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.29 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction Source checking is not independent reproduction.
TAPE Transformer: ProteinNet CASP12 Model: TAPE TransformerTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.36 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction Source checking is not independent reproduction.
ResNet (no pretraining): ProteinNet CASP12 Configuration: ResNet (no pretraining)Task: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.20 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row3(No pretraining/ResNet),columnContact prediction Source checking is not independent reproduction.
LSTM (no pretraining): ProteinNet CASP12 Configuration: LSTM (no pretraining)Task: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.19 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row2(No pretraining/LSTM),columnContact prediction Source checking is not independent reproduction.
TAPE Unirep: ProteinNet CASP12 Model: TAPE UnirepTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Independent external evaluation · Evaluation metadata: needs review
0.34 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction Source checking is not independent reproduction.
Alignment: ProteinNet CASP12 Configuration: AlignmentTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.64 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Source checking is not independent reproduction.
TAPE LSTM: ProteinNet CASP12 Model: TAPE LSTMTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.39 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction Source checking is not independent reproduction.
Transformer (no pretraining): ProteinNet CASP12 Configuration: Transformer (no pretraining)Task: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.32 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnContact prediction Source checking is not independent reproduction.
TAPE Bepler: ProteinNet CASP12 Model: TAPE BeplerTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.40 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction Source checking is not independent reproduction.
TAPE One Hot: ProteinNet CASP12 Method: TAPE One HotTask: TAPE Contact PredictionDataset: ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review
0.29 precision at L/5 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedtape primary benchmark evidence · Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction Source checking is not independent reproduction.

Evidence table

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.

7 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
attributes.reported_population.count 40 Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.reported_population.count` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.reported_population.unit proteins; top L/5 pairs per protein Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.reported_population.unit` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.source_locator Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.split CASP12 test, 30% sequence-identity partition; medium/long-range contacts Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.split` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.subset No value recorded Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	missing or unspecified No individual claim review recorded Audit details Field: `attributes.subset` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
description Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage. Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	not individually reviewed No individual claim review recorded Audit details Field: `description` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
name ProteinNet CASP12 Context-only references	tape primary benchmark evidence Original source ↗ Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction Version: 1906.08230v1 Retrieved: 2026-09-16T20:23:48.238777+00:00	not individually reviewed No individual claim review recorded Audit details Field: `name` Source artifact SHA-256: `6ee0c3e6e870635cba8fa67e0a4abc5598c0ab2a10ba127a46b67ac450ae0168` 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

tape primary benchmark evidence · Original source · 1906.08230v1

Download this release

Technical metadata and extraction receipts

Stable ID: paper-dataset-b2114365a5517543b7

areas: protein-function
split: CASP12 test, 30% sequence-identity partition; medium/long-range contacts
subset: Not reported
reported population: count: 40; unit: proteins; top L/5 pairs per protein
source locator: Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction
missing metadata: manifest: unextracted; scored count: unreported
entity classification: review date: 2026-09-17; rationale: This record identifies a biological data collection or source-labelled evaluation cohort. Keep its dataset identity; split, assay, taxonomic level, candidate restrictions and comparison context remain attributes rather than automatically becoming new entity kinds.; source ids: evidence-discovery-final-tape; source locator: Results on downstream supervised tasks; Table2,p.7,row1(No pretraining/Transformer),columnContact prediction; Table2,p.7,row2(No pretraining/LSTM),columnContact prediction; Table2,p.7,row3(No pretraining/ResNet),columnContact prediction; Table2,p.7,row4(Self-supervised pretraining/Transformer),columnContact prediction; Table2,p.7,row5(Self-supervised pretraining/LSTM),columnContact prediction; Table2,p.7,row6(Self-supervised pretraining/ResNet),columnContact prediction; Table2,p.7,row7(Supervised pretraining/Bepler supervised LSTM),columnContact prediction; Table2,p.7,row8(Self-supervised pretraining/UniRep mLSTM),columnContact prediction; Table2,p.7,row9(One-hot baseline/One-hot),columnContact prediction; Table2,p.7,row10(Task-specific alignment/HMM baseline/Alignment),columnContact prediction; ambiguities: None recorded

Related records

dataset: Alignment: ProteinNet CASP12
dataset: LSTM (no pretraining): ProteinNet CASP12
dataset: TAPE Bepler: ProteinNet CASP12
dataset: TAPE Unirep: ProteinNet CASP12
dataset: TAPE Transformer: ProteinNet CASP12
dataset: Transformer (no pretraining): ProteinNet CASP12
dataset: TAPE LSTM: ProteinNet CASP12
dataset: ResNet (no pretraining): ProteinNet CASP12
dataset: TAPE ResNet: ProteinNet CASP12
dataset: TAPE One Hot: ProteinNet CASP12

Suggest a correction