FlowingFlowing
← 返回全部开发案例
开发阶段案例 · 模型盲评尚待独立人工复核，不代表正式 Benchmark 结论。
自动补全两组均不可用89 / 162 · cf64b9ac8ea7c26b

A Review of BioTree Construction in the Context of Information Fusion: Priors, Methods, Applications and Trends

定量生物学 · 2410.04815v2

FLOWING EVIDENCE BENCHMARK

怎么判断 Evidence 真的有帮助？

核心问题是：在同一写作位置、使用同一模型和任务时，提供检索文献片段会怎样改变首次输出？我们成对比较两种条件，保留持平、不可用和评审未完成的结果。

同一段原稿 · 比较是否提供 Evidence

01 · 固定写作位置

论文原稿

同一处写作点位 ▌

同一原稿位置的自动补全成对比较

02 · 构造两组输入

两组共用

原稿上下文、模型、任务和提示词

A · 提供 Evidence

额外提供检索文献片段

B · 不提供 Evidence

不提供检索文献片段

LLM

同一模型、同一版本

A → 首次输出

B → 首次输出

盲评 Agent

匿名标记两份首次输出为 X、Y

按续写质量判断：准确性、任务贴合度和可用性
输出：X 更优 / 持平 / Y 更优 / 两组均不可用

换序复评：X / Y → Y / X

盲评具体怎么判？

① 匿名两份输出
评审看到同一原稿和两份首次输出，但不知道哪份用了 Evidence。

② 比较并换序复评
根据当前任务的标准，按 X/Y、再按 Y/X 的顺序各评一次。

③ 复核分歧
两次结论不一致时再做第三次判定；未完成的评审也留在分母。

自动补全点位怎样分层？

在查看生成结果前，先核查检索片段是否含有能直接支撑下一步续写的具体命题；有则放在左侧机会组，否则放在右侧普通组。每个学科从可准入论文中均衡选取两组点位。50/50 是实验设计，不代表真实写作中两类点位各占一半。

AUTOCOMPLETE · 110

定量生物学、统计学、天体物理学

左侧 55 个、右侧 55 个点位；统计学采用 10 篇论文的复测结果。

AUTOCOMPLETE · 52

心理学与气候科学

左侧 26 个、右侧 26 个点位；心理学计入 9 篇，气候科学计入 4 篇。

表格里的百分比怎么算？

五学科共有 81 个左侧点位。原始盲评有 51 个 Evidence 胜出；任务校验将其中一条空白续写改归“两组均不可用”，因此公开统计为 50 个。普通组另有一条双方空白，已从“未分出胜负”改归“两组均不可用”。这些原始判定仍可在案例页查看。

50Evidence 版本更优
÷
81该层全部点位
=
62%该层 Evidence 获评更优的比例

来源贡献是另一项复核：已进入复核的 21 个 Evidence 获胜点位中，16 个确认直接使用了检索论文；另有 29 个胜出点位尚待复核。

当前是开发阶段的模型评审结果，尚未完成独立人工复核；这些数字不代表正式 Benchmark 结论，也不能单独证明因果关系。

原始模型判定为“Evidence 更优”。任务校验发现空白输出不能算作可用续写，因此公开统计归为“两组均不可用”。原始判定和理由保留在下方。

原稿写作位置

原文摘录 · 非 PDF 页面

研究论文 · 原文片段

A Review of BioTree Construction in the Context of Information Fusion: Priors, Methods, Applications and Trends

6 Classical BioTree Construction Methods > 6.5 Limitations of Traditional BioTree Construction Methods

Similarity matrix-based methods utilize a cell-to-cell similarity matrix to analyze relationships between cells and construct lineage trees based on these similarities. SoptSC [ 298 ] builds a lineage tree by performing clustering and lineage inference using cell-cell relationships derived from a similarity matrix, effectively capturing the hierarchical differentiation paths in a tree structure.

…ccount for noise and stochasticity in gene expression profiles while constructing lineage trees. cellTree [ 65 ] models the gene expression data using a probabilistic framework to construct a tree-like structure that outlines hierarchical differentiation, explicitly representing cell lineages as branches of a tree. CALISTA [ 214 ] integrates clustering, lineage progression, transition gene identification, and pseudotime ordering into a unified framework, constructing lineage trees that represent the developmental trajectories of cells based on statistical modeling of gene expression patterns.

↓ 此处生成下一段续写

黄色标出写作点位附近的原文；本页根据评测输入重排文本，不是原始 PDF 截图。

同一写作位置的成对对照公开统计结果：两组均不可用

两组使用同一模型、同一写作任务和原稿上下文，仅比较是否提供检索文献片段。下方展示评测记录中的首次输出。

Evidence

同一模型与写作位置 · 提供检索文献片段 · 首次输出

任务校验归为不可用

产品最终没有可插入的续写正文。

模型原始响应包含续写正文，但当时的产品校验将其拦截并标记为需要证据；原始正文尚未在此独立核查。

提供给 Evidence 版本的文献片段

Reconstructing probabilistic trees of cellular differentiation from single-cell RNA-seq data ↗

Thanks to technological advances, we can now profile gene expression across thousands or millions of individual cells in parallel. This new type of data has led to the intriguing discovery that individual cell profiles can reflect the imprint of time or dynamic processes. However, synthesizing this…

展开完整文献摘录

Thanks to technological advances, we can now profile gene expression across thousands or millions of individual cells in parallel. This new type of data has led to the intriguing discovery that individual cell profiles can reflect the imprint of time or dynamic processes. However, synthesizing this information to reconstruct dynamic biological phenomena from data that are noisy, heterogenous, and sparse—and from processes that may unfold asynchronously—poses a complex computational and statistical challenge. Here, we develop a full generative model for probabilistically reconstructing trees of cellular differentiation from single-cell RNA-seq data. Specifically, we extend the framework of the classical Dirichlet diffusion tree to simultaneously infer branch topology and latent cell states along continuous trajectories over the full tree.

无 Evidence

同一模型与写作位置 · 不提供检索文献片段 · 首次输出

任务校验归为不可用

Despite these capabilities, similarity matrix-based methods face several inherent limitations. Their performance depends heavily on the accuracy of the estimated cell-to-cell similarity matrix, which is sensitive to noise, dropout events, and the choice of distance metric.

评审结论与任务校验

公开统计归为两边都不可用；空白续写不能完成本任务。

查看模型评审原始理由（英文）

原始理由中的 Output A = 无 Evidence，Output B = Evidence。

Output A adds material factual claims that are not supported by the draft or supplied sources. It states that similarity matrix-based methods 'face several inherent limitations,' that their performance 'depends heavily on the accuracy of the estimated cell-to-cell similarity matrix,' and that this matrix 'is sensitive to noise, dropout events, and the choice of distance metric.' None of these claims appear in the draft text, which only describes methods and their approaches without evaluating limitations. The single supplied source discusses cellTree's probabilistic framework and general challenges of single-cell RNA-seq data (noisy, heterogeneous, sparse, asynchronous), but does not mention similarity matrix-based methods, their limitations, dropout events, or distance metric sensitivity. The source's general discussion of noise and sparsity in single-cell data does not support specific limitations of similarity matrix-based methods. Output B correctly returns an empty result with 'needs_evidence' action, acknowledging that no supplied source directly supports a completion for this blank paragraph.

文献片段是输入材料；出现于此不代表输出使用了它，也不代表它能够支持全部主张。原文与检索片段经过截取；页面没有展示模拟分数或模拟 PDF。