In an Agents4Science case study, the paper claimed SciBERT embeddings with 768 dimensions, but all three relevant released files configured all-MiniLM-L6-v2 and produced 384-dimensional vectors; SciBERT was not imported anywhere.

In an Agents4Science case study, the paper claimed SciBERT embeddings with 768 dimensions, but all three relevant released files configured all-MiniLM-L6-v2 and produced 384-dimensional vectors; SciBERT was not imported anywhere. · CiteArk

测量结果

已评估 0/3 项

获得支持 0有争议或冲突 0尚未评估 3

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
source: paper claim · encoder: SciBERT	768 dimensions	—	尚未评估
source: released code · encoder: all-MiniLM-L6-v2	384 dimensions	—	尚未评估
	3 files	—	尚未评估

In an Agents4Science case study, the paper claimed SciBERT embeddings with 768 dimensions, but all three relevant released files configured all-MiniLM-L6-v2 and produced 384-dimensional vectors; SciBERT was not imported anywhere.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果