Result

40.41(1.67)% precision_at_l

LSTM · BEACON CMP · Top L Precision

Tested method: LSTM
Task: BEACON CMP: Contact map prediction
Dataset subset: RNAcontact (BEACON split)
Procedure: BEACON harness, fixed downstream head per task. Train/validation/test 188/23/80; dataset RNAcontact.
Evaluation: LSTM on BEACON CMP: Contact map prediction
Evidence: Author-reported evaluation · source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(LSTM),column(CMP)

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Methods and reproduction

BEACON harness evaluation of LSTM on Contact map prediction, scored with Top L Precision.

task: BEACON CMP: Contact map prediction
method: LSTM
dataset subset: RNAcontact (BEACON split)
Split: 188/23/80
Adaptation: Naive supervised model trained from scratch by the BEACON authors
Scoring implementation: Top L Precision

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Access requirements and official instructions: BEACON CMP: Contact map prediction

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evaluation results

Release 2026-09-17-1a18ca2c038a · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
LSTM on BEACON CMP: Contact map prediction Method: LSTMTask: BEACON CMP: Contact map predictionDataset subset: RNAcontact (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 188/23/80; dataset RNAcontact. Author-reported evaluation · Evaluation metadata: source checked
40.41(1.67)% precision_at_l Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 1.67 Scored: Not reported · Eligible: Not reported	source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(LSTM),column(CMP) Source checking is not independent reproduction.

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-1a18ca2c038a
Property and statement	Original source and location	Review and provenance
Reported result 40.41(1.67) Individual claims	BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) Original source ↗ Table3,p.8,row(LSTM),column(CMP) Version: v2, 12 December 2024 Retrieved: 2026-09-18	source checked Deterministic parse of the pinned PDF text layer, with row and cell counts asserted and ten values cross-checked against the printed table · 2026-09-18 author reported Audit details Source checked, not reproduced. Metrics differ by task, so no composite score across tasks is computed or implied. Field: `attributes.printed_value` Source artifact SHA-256: `1370d75fe591bb8f994bc67f100a1a3fd557a62b9edb962b21f2fb038e9dea16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `1370d75fe591bb8f994bc67f100a1a3fd557a62b9edb962b21f2fb038e9dea16` Extraction artifact

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

Sources and history

Release 2026-09-17-1a18ca2c038a · Record review: source checked

1 source records and release history

BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Original source · v2, 12 December 2024

Download this release

Technical metadata and extraction receipts

Stable ID: beacon-result-lstm-cmp-precision-at-l

areas: rna-transcriptomes
tasks: Contact map prediction
metric: precision_at_l
metric direction: higher
unit: percent
printed value: 40.41(1.67)
numeric value: 40.41
uncertainty: type: standard_deviation; value: 1.67
source locator: Table3,p.8,row(LSTM),column(CMP)
missing metadata: denominator: unextracted; seeds: unreported
review: method: Deterministic parse of the pinned PDF text layer, with row and cell counts asserted and ten values cross-checked against the printed table; reviewer: Codex research agent; no human review claimed; date: 2026-09-18; artifact sha256: 1370d75fe591bb8f994bc67f100a1a3fd557a62b9edb962b21f2fb038e9dea16; retrieval url: https://arxiv.org/pdf/2406.10391; notes: Source checked, not reproduced. Metrics differ by task, so no composite score across tasks is computed or implied.

Related records

evaluation: LSTM on BEACON CMP: Contact map prediction

Suggest a correction