FlowingFlowing
← Back to all development cases
This case was judged by an anonymized AI reviewer and has not been independently reviewed by people; inspect the draft, cards, and both outputs to assess it.
AutocompleteWithout cards better5 / 280 · beu-265f9f8e2509097b

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

Quantitative biology · 2410.04815v2

FLOWING EVIDENCE BENCHMARK

How do we compare writing with and without cards?

At the same writing position, the same model produces one first result with cards and one without. All 280 pairs enter the overall anonymized review, which assesses whether a decision not to continue fits the draft.

Overall: 138 with-card wins, 26 ties, 107 no-card wins, 5 pairs where neither was usable, and 4 inconclusive judgments. Both sides wrote text in 218 pairs; 48 had a deliberate stop and 14 included an invalid output.

SAME DRAFT · WITH OR WITHOUT CARDS

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED VERSIONS

SHARED BY BOTH

Draft, writing task, and generation model

A · With cards

Relevant literature cards supplied

B · Without cards

No literature cards supplied

Generation model

Same model and version

A → first output

B → first output

Anonymized AI judge

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Review again with the answer order swapped

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The AI judge sees the same draft and both first outputs without knowing which received cards.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are positions and cards selected?

We selected 40 writing positions in each of seven fields, for 280 comparisons. The position and relevant literature cards were set before each comparison, so both versions began from the same draft.

The main result retains every frozen position, including places where cards might not add a useful next move. This avoids selecting cases based on their outputs, but 49% describes the whole cohort, not a win rate where evidence clearly had an opportunity to help. This cohort did not record that opportunity label for each position before generation, so those two groups cannot yet be separated reliably.

CARD USE · 140/280

Reported card use in continuations with text

The model reports whether a card affected its continuation. In 140 of 280 tests it produced continuation text and reported card use. The previous count of 150 included 10 cases without continuation text and has been corrected.

COMPARISON · 70 / 7 / 30

Which written version was better?

Of the 107 reported-use cases where both versions produced text, the blinded AI judge preferred the with-card version 70 times, found 7 about the same, and preferred the without-card version 30 times.

How are the two table percentages calculated?

ADOPTION COVERAGE

140reported use with text
÷
280all positions
=
50%

WITH-CARD VERSION PREFERRED

70with cards better
÷
107comparable tests
=
65%

The percentages use different groups: 50% counts continuations with text reporting card use among all 280 tests; 65% covers the 107 such cases with text on both sides. The generating model reports card use, while an anonymized AI judge compares writing quality.

Card use is self-reported by the generator. The anonymized AI judge sees the draft and source snippets, so source-aware preference remains possible; there was no independent human review. The overall result describes these 280 frozen positions, not a win probability for any writing task.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

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.

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionOverall AI review: Without cards better

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Read overall AI review rationale

A = with cards · B = without cards

Both outputs attempt a similar transition: moving from describing specific methods to identifying limitations of 'classical/traditional' BioTree construction methods. However, Output B is more precise and better fitted to the draft context. The draft specifically discusses scRNA-seq methods (SoptSC, cellTree, CALISTA), and Output B explicitly names 'scRNA-seq' as the typical data modality, which accurately reflects the visible draft. Output B also provides concrete examples of complementary information ('spatial context or protein-level measurements') that are relevant to current single-cell biology. Output A's 'gene expression or morphological features' is less precise—morphological features aren't mentioned in the draft, and 'gene expression' understates that these are specifically single-cell transcriptomic methods. Output A's 'BioTree' appears to be a typo or invented term (the draft uses 'lineage tree'), though this is minor. Both are usable, but Output B demonstrates better scope calibration and fit to the specific argument in progress.

Evidence

Same model and position · retrieved passages supplied · first output

Not preferred in this comparison

Despite these advances, traditional BioTree construction methods share several limitations. Most rely on a single data modality, such as gene expression or morphological features, and therefore cannot exploit the complementary information available from other sources.

Passages supplied to the Evidence version

Card 1 · Reconstructing probabilistic trees of cellular differentiation from single-cell RNA-seq data

Until recently, transcriptomics was limited to bulk RNA sequencing, obscuring the underlying expression patterns of individual cells in favor of a global average. Thanks to technological advances, we can now profile gene expression across thousands or millions of individual cells in parallel. This n…

Read full passage excerpt

Until recently, transcriptomics was limited to bulk RNA sequencing, obscuring the underlying expression patterns of individual cells in favor of a global average. 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 ove …

Card 2 · Modelling-based experiment retrieval: a case study with gene expression clustering

MOTIVATION: Public and private repositories of experimental data are growing to sizes that require dedicated methods for finding relevant data. To improve on the state of the art of keyword searches from annotations, methods for content-based retrieval have been proposed. In the context of gene expr…

Read full passage excerpt

MOTIVATION: Public and private repositories of experimental data are growing to sizes that require dedicated methods for finding relevant data. To improve on the state of the art of keyword searches from annotations, methods for content-based retrieval have been proposed. In the context of gene expression experiments, most methods retrieve gene expression profiles, requiring each experiment to be expressed as a single profile, typically of case versus control. A more general, recently suggested alternative is to retrieve experiments whose models are good for modelling the query dataset. However, for very noisy and high-dimensional query data, this retrieval criterion turns out to be very noisy as well. RESULTS: We propose doing retrieval using a denoised model of the query dataset, instead of the original noisy dataset itself. To this end, we introduce a general probabilistic framework, where each experiment is modelled separately and the retrieval is done by finding related models. Fo …

Card 3 · A hidden spatial-temporal Markov random field model for network-based analysis of time course gene expression data

Microarray time course (MTC) gene expression data are commonly collected to study the dynamic nature of biological processes. One important problem is to identify genes that show different expression profiles over time and pathways that are perturbed during a given biological process. While methods…

Read full passage excerpt

Microarray time course (MTC) gene expression data are commonly collected to study the dynamic nature of biological processes. One important problem is to identify genes that show different expression profiles over time and pathways that are perturbed during a given biological process. While methods are available to identify the genes with differential expression levels over time, there is a lack of methods that can incorporate the pathway information in identifying the pathways being modified/activated during a biological process. In this paper we develop a hidden spatial-temporal Markov random field (hstMRF)-based method for identifying genes and subnetworks that are related to biological processes, where the dependency of the differential expression patterns of genes on the networks are modeled over time and over the network of pathways. Simulation studies indicated that the method is quite effective in identifying genes and modified subnetworks and has higher sensitivity than the co …

Card 4 · Shared Differential Clustering across Single-cell RNA Sequencing Datasets with the Hierarchical Dirichlet Process

Single-cell RNA sequencing (scRNA-seq) is powerful technology that allows researchers to understand gene expression patterns at the single-cell level. However, analysing scRNA-seq data is challenging due to issues and biases in data collection. In this work, we construct an integrated Bayesian model…

Read full passage excerpt

Single-cell RNA sequencing (scRNA-seq) is powerful technology that allows researchers to understand gene expression patterns at the single-cell level. However, analysing scRNA-seq data is challenging due to issues and biases in data collection. In this work, we construct an integrated Bayesian model that simultaneously addresses normalization, imputation and batch effects and also nonparametrically clusters cells into groups across multiple datasets. A Gibbs sampler based on a finite-dimensional approximation of the HDP is developed for posterior inference.

Card 5 · Role of Spatial Averaging in the Precision of Gene Expression Patterns

During embryonic development, differentiating cells respond via gene expression to positional cues from morphogen gradients. While gene expression is often highly erratic, embryonic development is precise. We show by theory and simulations that diffusion of the expressed protein can enhance the prec…

Read full passage excerpt

During embryonic development, differentiating cells respond via gene expression to positional cues from morphogen gradients. While gene expression is often highly erratic, embryonic development is precise. We show by theory and simulations that diffusion of the expressed protein can enhance the precision of its expression domain. While diffusion lessens the sharpness of the expression boundary, it also reduces super-Poissonian noise by washing out bursts of gene expression. Balancing these effects yields an optimal diffusion constant maximizing the precision of the expression domain.

Model-reported card use

The model did not report that any card materially affected this completion.

No Evidence

Same model and position · no retrieved passages · first output

Preferred by blind review

Despite these advances, classical BioTree construction methods still face several limitations. Most of these approaches rely on a single data modality, typically scRNA-seq, and therefore cannot exploit complementary information such as spatial context or protein-level measurements.

Earlier card-use comparison

The earlier diagnostic compared only cases with reported card use and text on both sides; its scope differs from the overall AI review above.

This case does not have both with-card continuation text and a model-reported use record. It remains among all 280 tests but does not enter the reported-use comparison.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.