Result

0.11487652025892987 score_avg

Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe] · score_avg · 2026 validation contexts A, B and C

Tested configuration: Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe]
Protocol: vcc2026-val-1 · 2026 validation contexts A, B and C
Dataset subset: 2026 validation contexts A, B and C
Procedure: vcc2026-val-1
Evaluation: Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe] · vcc2026-val-1 · 2026 validation contexts A, B and C
Evidence: Author-reported evaluation · source checkedVirtual Cell Challenge 2026: 2026-09-19 snapshot; panel vcc2026-val-1 · JSON entries[295].score_avg; submission MDZhGPwc7ILcaeDrb5qe

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

Evaluation results

Release 2026-09-19-eb6149e5d766 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard. Charts retain each source table’s protocol and dataset.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe] · vcc2026-val-1 · 2026 validation contexts A, B and C Configuration: Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe]Protocol: vcc2026-val-1 · 2026 validation contexts A, B and CDataset subset: 2026 validation contexts A, B and C vcc2026-val-1 Author-reported evaluation · Evaluation metadata: discovered
0.11487652025892987 score_avg Unit: score · Direction: higher Aggregation: unreported	Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported	source checkedVirtual Cell Challenge 2026: 2026-09-19 snapshot; panel vcc2026-val-1 · JSON entries[295].score_avg; submission MDZhGPwc7ILcaeDrb5qe Source checking is not independent reproduction.

Methods and reproduction

vcc2026-val-1; 2026 validation contexts A, B and C. Source checked, not independently reproduced.

configuration: Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe]
protocol: vcc2026-val-1 · 2026 validation contexts A, B and C
dataset subset: 2026 validation contexts A, B and C
Split: 2026 validation contexts A, B and C
Adaptation: unreported
Scoring implementation: Not reported

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: vcc2026-val-1 · 2026 validation contexts A, B and C

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.

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 2026-09-19-eb6149e5d766
Property and statement	Original source and location	Review and provenance
Reported result 0.11487652025892987 Individual claims	Virtual Cell Challenge 2026: 2026-09-19 snapshot; panel vcc2026-val-1 Original source ↗ JSON entries[295].score_avg; submission MDZhGPwc7ILcaeDrb5qe Version: 2026-09-19 snapshot; panel vcc2026-val-1 Retrieved: 2026-09-19	source checked independent automated cell check and ai scope review · 2026-09-19 author reported Audit details Transcription checked independently. No human review or scientific reproduction claimed. Field: `attributes.printed_value` Source artifact SHA-256: `85eacc0c1e9067231f84607715f4d94a52e5115e4758cfbaed65898621e96103` Hash scope: Exact downloaded bytes, before optional gzip storage Inspected artifact Extraction artifact SHA-256: `85eacc0c1e9067231f84607715f4d94a52e5115e4758cfbaed65898621e96103`

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

Sources and history

View linked audit checks and correction history

Release 2026-09-19-eb6149e5d766 · Record review: source checked

1 source records and release history

Virtual Cell Challenge 2026: 2026-09-19 snapshot; panel vcc2026-val-1 · Original source · 2026-09-19 snapshot; panel vcc2026-val-1

Download this release

Technical metadata and extraction receipts

Stable ID: acquired-result-f9305db2d8808bad33e8

metric: score_avg
metric direction: higher
unit: score
printed value: 0.11487652025892987
numeric value: 0.11487652025892987
uncertainty: status: unreported
aggregation: unreported
scoring conditions: anchor version: vcc2026-valA-r4+vcc2026-valB-r4+vcc2026-valC-r4; is final: false; model name reported: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier; notes: Provisional overall validation score only. Team/model labels do not establish a catalogue model identity; do not infer family aliases. Final test results unavailable at snapshot date.; snapshot date: 2026-09-19; submission date: 2026-09-19T08:41:33.922599Z; submission id: MDZhGPwc7ILcaeDrb5qe; team id: WH21no458hHi2t1378bd
source locator: JSON entries[295].score_avg; submission MDZhGPwc7ILcaeDrb5qe
acquisition candidate id: candidate-83a2a82e51bc5d3daf7e
missing metadata: denominator: unreported
review: method: independent_automated_cell_check_and_ai_scope_review; date: 2026-09-19; artifact sha256: 85eacc0c1e9067231f84607715f4d94a52e5115e4758cfbaed65898621e96103; receipt: data/omics/acquisition/2026-09-19/cells-networks/; notes: Transcription checked independently. No human review or scientific reproduction claimed.

Related records

evaluation: Naoto Otsuka: v49: equal-weight ensemble of two nearly independent predictors - the K562-only transfer (0.0865 alone) and the three-screen transfer (0.0786 alone), whose predicted log2 fold changes correlate at only rho 0.076. Averaging happens after prediction rather than inside the library blend, which is why it is a different operation from the multi-source entries that lost ground earlier [submission MDZhGPwc7ILcaeDrb5qe] · vcc2026-val-1 · 2026 validation contexts A, B and C

Suggest a correction