Coverage

blocked upstream · v5 provisional awaiting approval

What does the paper assert that no claim represents?

for A deep learning pipeline for mapping in situ network-level neurovascular coupling in multi-photon fluorescence microscopy · this layer across all papers · json

Provisional

This layer needs a corpus-scope decision that has not been ruled on yet, so what it produces would change if the decision changed. It waits on claim-format, relation-vocab.

Awaiting approval

Waiting for approval. That is a statement about the record, not about whether anyone has read this: people read the corpus without stamping what they read, and only a stamp leaves a trace. Approval is an operation on a version, not a step of its own — it is recorded against the version it was granted to, so running this layer again does not carry it forward.

What it produced40 spans.orphans

Read from coverage/rozak-2026-neurovascular-dl.json · 14 KB. claims 24panels.pct 16.3statistics.total 10statistics.pct 30spans.segmented 302spans.obligations 83spans.textual 219spans.accounted 43spans.pct 51.8

#	uid	section	text	stats	panels
1	results-010	results	The Dice, precision, recall, mean surface distance, and HD95 distance for the vascular ( A ) and neuron ( B ) channels.	`[]`	`["fig3a","fig3b"]`
2	results-014	results	( A ) Raw images of the vascular channel with the neuron channel subtracted to facilitate vessel visualization.	`[]`	`["fig4a"]`
3	results-017	results	( B ) Ground truth segmentation masks for the vasculature were generated by a rater who utilized ilastik-assisted manual segmentation.	`[]`	`["fig4b"]`
4	results-018	results	( C ) Ilastik predictions generated via a random forest model.	`[]`	`["fig4c"]`
5	results-019	results	( D ) Binary segmentation masks generated by an ensemble of 3D UNet models.	`[]`	`["fig4d"]`
6	results-020	results	( E ) Binary segmentation masks generated by an ensemble of 3D UNETR models.	`[]`	`["fig4e"]`
7	results-029	results	Across > 100,000 simulations, the fit of the estimated radius following rescaling against the simulated radius had an R 2 value of 0.68. Figure 5B presents a heatmap of the estimated radius post-scali…	`[]`	`["fig5b"]`
8	results-032	results	( A ) An image in the plane orthogonal to the local tangent to a capillary with the detected boundary (in blue) and with the estimated radius of 2.28 μm.	`[]`	`["fig5a"]`
9	results-034	results	( B ) The plot shows correspondence between the estimated radius following scaling and the simulated level of scaling.	`[]`	`["fig5b"]`
10	results-035	results	( C ) An image in the plane orthogonal to the local tangent of a capillary with the detected boundary (in blue) and with the estimated radius of 3.65 μm.	`[]`	`["fig5c"]`
11	results-037	results	( D ) The estimated % change in the vessel’s radius after the addition of varying levels of Gaussian noise, demonstrating the robustness of the radius estimated to noise.	`[]`	`["fig5d"]`
12	results-043	results	As the amount of averaging increased, the uncertainty on the diameter of the beads decreased, and our estimate of the bead’s diameter converged upon the manufacturer’s Coulter counter-based specificat…	`[]`	`["table1"]`
13	results-044	results	Table 1. Bead diameter estimates.	`[]`	`["table1"]`
14	results-049	results	To highlight the ability of the pipeline to detect vessels that significantly change their radius after stimulation, Figure 6A shows the standard deviation of the average radii on each vessel segment …	`[]`	`["fig6a"]`
15	results-051	results	We examined the average change in the vascular radius of each vessel segment after vs. before photostimulation ( Figure 6B ), with even finer spatial patterns detected by analyzing the vertex-wise rad…	`[]`	`["fig6b","fig6c"]`
16	results-052	results	The vascular diameter changes were related to the distance from the vessel’s surface to the closest labeled pyramidal neuron at each vertex of the centerline ( Figure 6D ).	`[]`	`["fig6d"]`
17	results-057	results	Table 2. S1FL vascular network morphological properties.	`[]`	`["table2"]`
18	results-059	results	( A ) Baseline variability in vessel diameter estimated by the standard deviation of each vessel’s mean radius across baseline time frames.	`[]`	`["table2a"]`
19	results-060	results	( B ) Mean change in the vessel radius induced by optogenetic stimulation.	`[]`	`["table2b"]`
20	results-061	results	( C ) Mean change in the vertexwise radius, allowing the visualization of heterogeneity of radius changes within each vessel.	`[]`	`["table2c"]`
21	results-062	results	( D ) Distance from each vertex to the closest pyramidal neuron.	`[]`	`["table2d"]`
22	results-067	results	( B ) Estimates of the vertex-wise radius obtained along each of the three vessels’ centrelines, before and after stimulation.	`[]`	`["fig7b"]`
23	results-068	results	( C ) Vertex-wise radii changes in response to optogenetic stimulation.	`[]`	`["fig7c"]`
24	results-069	results	( D ).	`[]`	`["fig7d"]`
25	results-074	results	The morphometric properties of the responders, under different stimulation conditions, are listed in Table 3 .	`[]`	`["table3"]`
26	results-081	results	Table 3. Details of responder (Δ R >2 * σR baseline ) vessels.	`[]`	`["table3"]`
27	results-084	results	( C ) Probability density function of constrictions and dilations for the 4.3 mW/mm 2 photostimulation.	`[]`	`["table3c"]`
28	results-085	results	( D ) Changes to capillary radii are displayed in relation to the closest pyramidal neurons.	`[]`	`["table3d"]`
29	results-087	results	( E ) Mean cortical depth of responding capillaries showed a tendency for dilators to be closer to the surface and for constrictors to be deeper in the tissue.	`[]`	`["table3e"]`
30	results-094	results	For constrictions, 458 nm photostimulations led to –1.39±1.51 μm radius changes with 1.1 m W m m 2 \begin{document}$\frac{mW}{mm^{2}}$\end{document} and –1.20±1.13 μm radius changes with 4.3 m W m m 2…	`["p=4.4e-3","p=0.02"]`	`[]`
31	results-102	results	( A ) Graph representation of a vascular network of 425 vascular segments from a single image stack.	`[]`	`["fig9a"]`
32	results-108	results	There was a significant increase (p=0.03) in the capillary network efficiency post 458 nm light at 4.3 mW/mm 2 , when compared to that following the control green illumination.	`["p=0.03"]`	`[]`
33	discussion-063	discussion	Example slices of the segmentation results are shown in Appendix 1—figure 10 .	`[]`	`["fig10"]`
34	discussion-068	discussion	Visualizations of the two graphs are shown in Appendix 1—figure 11 .	`[]`	`["fig11"]`
35	discussion-077	discussion	Our vascular segmentation model generalized well to C57BL/6J mouse and Fischer rat data, as well as to Thy1-ChR2 light-sheet fluorescence microscopy images gathered on an UltraMicroscope Blaze lightsh…	`[]`	`["fig12","table3"]`
36	discussion-085	discussion	Additionally, alternative definitions of responding vessels may be useful depending on the end goal of a study (e.g. selecting a threshold for the radius change based on a percentage change from the b…	`[]`	`["fig14"]`
37	captions-003	captions	The emitted light passes through the objective, is reflected off the FV30-NDM690 dichroic mirror, and passes through a 650 nm barrier filter before reaching a 570 nm long pass filter (LPF) separating …	`[]`	`["fig2"]`
38	captions-061	captions	There was a significant increase (p=0.03) in the capillary network efficiency post 458 nm light at 4.3 mW/mm 2 , when compared to that following the control green illumination.	`["p=0.03"]`	`[]`
39	tables-001	tables	Table 1. Bead diameter estimates.	`[]`	`["table1"]`
40	tables-002	tables	Number of orthogonal planes Number of spokes per plane Mean diameter estimate (μm) 1 3 7.54±0.68 2 4 7.44±0.51 4 12 7.34±0.38 10 36 7.34±0.32 Table 2. S1FL vascular network morphological properties.	`[]`	`["table2"]`

Artifacts

coverage/rozak-2026-neurovascular-dl.json

Versions

From the run ledger. There is no changelog beside it to keep in step.

v5 · 2026-09-13 · scripts/pipeline.py run

ran via scripts/pipeline.py

cd extract && python3 -m elife_extract.cli coverage --paper rozak-2026-neurovascular-dl --json ../coverage/rozak-2026-neurovascular-dl.json
v4 · 2026-09-13 · scripts/pipeline.py run

ran via scripts/pipeline.py

cd extract && python3 -m elife_extract.cli coverage --paper rozak-2026-neurovascular-dl --json ../coverage/rozak-2026-neurovascular-dl.json
v3 · 2026-09-12 · scripts/pipeline.py run

re-run after prepare v2

cd extract && python3 -m elife_extract.cli coverage --paper rozak-2026-neurovascular-dl --json ../coverage/rozak-2026-neurovascular-dl.json
v2 · 2026-09-11 · scripts/pipeline.py run

coverage for the nine papers that had none

cd extract && python3 -m elife_extract.cli coverage --paper rozak-2026-neurovascular-dl --json ../coverage/rozak-2026-neurovascular-dl.json
v1 · 2026-09-11 · scripts/pipeline.py run

ran via scripts/pipeline.py

cd extract && python3 -m elife_extract.cli coverage --doi 10.7554/eLife.95525 --paper-slug rozak-2026-neurovascular-dl --claims-dir ../claims/rozak-2026-neurovascular-dl --json ../coverage/rozak-2026-neurovascular-dl.json

This layer across the corpus

Across the corpus

4 blocked upstream · 6 stale·a paper links to its own cell, where this layer's output for it is rendered

Paper	State	Version	Last run	Output	Cell
A three-dimensional immunofluorescence atlas of the …ran via scripts/pipeline.py	blocked upstream	v3	2026-09-13	artiushin-2026-spider-atlas.json	json
Distinct representational properties of cues and con…ran via scripts/pipeline.py	stale	v4	2026-09-13	bouyeure-2026-fear-rsa.json	json
Computational modelling identifies key determinants …ran via scripts/pipeline.py	stale	v3	2026-09-13	ejdrup-2026-dopamine.json	json
Contributions of insula and superior temporal sulcus…rebuild after edge completion pass	stale	v7	2026-09-13	gadeke-2026-guilt-insula.json	json
Spatially targeted inhibitory rhythms differentially…ran via scripts/pipeline.py	stale	v3	2026-09-13	headley-2026-inhibitory-rhythms.json	json
Feedback of peripheral saccade targets to early fove…ran via scripts/pipeline.py	blocked upstream	v3	2026-09-13	kammer-2026-foveal-feedback.json	json
iGABASnFR2 is an improved genetically encoded protei…ran via scripts/pipeline.py	blocked upstream	v5	2026-09-13	kolb-2026-igabasnfr2.json	json
A deep learning pipeline for mapping in situ network…ran via scripts/pipeline.py	blocked upstream	v5	2026-09-13	rozak-2026-neurovascular-dl.json	json
Self-association enhances early attentional selectio…ran via scripts/pipeline.py	stale	v3	2026-09-13	scheller-2026-self-prioritization.json	json
Impaired excitability of fast-spiking neurons in a n…ran via scripts/pipeline.py	stale	v5	2026-09-13	wengert-2026-kcnc1.json	json

Inputs and outputs

Produces: coverage/{paper}.json

One per paper — the table above links each one that exists.
Views: document — declared, and this artifact is not the shape this view needs
table — rendered above, over the 128 spans.orphans in the artifact

Running it

The command comes from the declaration, so this text and what actually runs cannot diverge. pipeline.py run also runs the unmet dependencies first.

python3 scripts/pipeline.py run <paper> coverage

Underneath, that runs cd extract && python3 -m claim_graphs.cli coverage --paper {paper} --json ../coverage/{paper}.json.