B16-TR01 · same_source_table
private postcompetition | ArmNet with BPPM postcompetition | ensemble 15
Ribonanza private test set
Protocol fingerprint
PF-v1-826854518D409623BC542805
The result chunk loads only after both the metric and protocol-metric fingerprint are selected.
- Split
- private leaderboard test set evaluated postcompetition
- Aggregation
- Table S5 mean absolute error after [0,1] clipping
- External data
- method-specific; not aligned for cross-method ranking
- Ensemble / best-of-N
- ArmNet BPPM postcompetition ensemble of 15 model(s) · 1
- Critical unknowns
- external_data_policy;inference_budget;postcompetition model-selection details
Interactive results
Filter and compare inside one fingerprint
Choose a metric and fingerprint to load results.
Top 50 rank-eligible results
Current fingerprint and filters only.
Same-fingerprint comparison
| Participant | Configuration | Score | Rank | Claim |
|---|
| Compare | Participant / configuration | Score | Ranks | Baseline / claim | Evidence & settings |
|---|
Complete protocol fields
- canonical dataset ids
- ribonanza_2023
- data version
- Table S5 postcompetition evaluation
- label visibility
- postcompetition evaluation; leaderboard/test feedback may be available
- input modality
- RNA sequence with method-specific structural/pair features
- preprocessing
- Table S5 postcompetition procedure; MAE clips predicted and experimental reactivity values to [0,1]
- model selection rule
- postcompetition method-specific selection
- inference budget
- NR
- protocol completeness
- exact_score_protocol_configuration_limited