CPPC original submission row 5 (scBERT)

Overview

Original submitted workflow identified by immutable Table S2 row, not by team personal details. Benchmark method-name column may identify a reimplementation/feature and does not establish an identical current model.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

2 evaluations · 2 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: CPPC original submission row 5 (scBERT)	Protocol: CPPC original Challenge 1 final four-knockout prediction score Dataset: CPPC B16-OVA mouse melanoma T-cell perturbation screens	0.767 mean-summed-cell-state-l1 summed absolute proportion error · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source cppc table s2 c row 5 Not reported Aggregation: Not reported CPPC Table S2 original and reimplemented submission comparisons · Supplementary Table S2; media-3.xlsx sheet 'Challenge 1 & 2'; cell C5; raw XLSX numeric value (not rounded display)
Configuration: CPPC original submission row 5 (scBERT)	Protocol: CPPC original Challenge 2 prospective target ranking score Dataset: CPPC B16-OVA mouse melanoma T-cell perturbation screens	0.508 robust-topk-overlap-auc score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source cppc table s2 d row 5 Not reported Aggregation: Not reported CPPC Table S2 original and reimplemented submission comparisons · Supplementary Table S2; media-3.xlsx sheet 'Challenge 1 & 2'; cell D5; raw XLSX numeric value (not rounded display)

Source checking is not independent reproduction. Release 2026-09-30-e37e3ab1284d.

Use this model

How it works, versions and access

Evidence

Source checking verifies the cited claim or transcription. It does not establish 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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-30-e37e3ab1284d
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

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

Sources and history

View linked audit checks and correction history

Release 2026-09-30-e37e3ab1284d · Record review: source checked

2 source records and release history

Cancer Immunotherapy Data Science Challenge · Original source · 10.64898/2026.05.21.726863v1; 2026 preprint
CPPC Table S2 original and reimplemented submission comparisons · Original source · Table S2 media-3.xlsx, 10.64898/2026.05.21.726863v1

Download this release

Technical metadata and extraction receipts

Stable ID: ucc-research-config-cppc-submission-row-5

review: method: automated_source_review; actor: Codex research coverage worker; reviewed at: 2026-09-30T21:43:56Z; note: Primary-source table transcription and scope review; no independent reproduction or human scientific review.
source row: 5
benchmark method label: scBERT
missing metadata: submission code revision: not extracted; checkpoint hash: not extracted

Related records

configuration: cppc table s2 c row 5
configuration: cppc table s2 d row 5