OSCR

High-rate phase association with travel time neural fields.

Code ↔ Paper

The paper beside its authors' code: matches between them have not been computed for this paper yet.

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 299 lines · 12 KB · MIT

  1. from torch.utils.data import Dataset, DataLoader
  2. import numpy as np
  3. from tqdm import tqdm
  4. import skfmm
  5. from obspy import UTCDateTime as UT
  7. import pandas as pd
  8. import multiprocessing
  10. class WaveSpeedDataset(Dataset):
  11. def __init__(self, V_trains, p_train):
  13. self.data_wavespeed=np.array(V_trains,dtype=np.float32)
  15. self.n_wavespeed=len(V_trains)
  16. self.p_train=np.array(p_train)
  18. def __len__(self):
  19. return self.n_wavespeed
  20. def __getitem__(self, idx):
  21. image = {'image':self.data_wavespeed[idx],'p': self.p_train}
  22. return image
  24. def get_traveling_time_multi(V_list,station_df,config,dx=25,align_station=False):
  25. station_df=station_df.copy()
  26. grid_size_x= int((config['x(km)'][1]-config['x(km)'][0])/dx+1)
  27. grid_size_y= int((config['y(km)'][1]-config['y(km)'][0])/dx+1)
  28. grid_size_z= int((config['z(km)'][1]-config['z(km)'][0])/dx+1)
  29. xx = np.linspace(config['x(km)'][0],config['x(km)'][1],grid_size_x)
  30. yy = np.linspace(config['y(km)'][0],config['y(km)'][1],grid_size_y)
  31. zz = np.linspace(config['z(km)'][0],config['z(km)'][1],grid_size_z)
  32. X, Y, Z = np.meshgrid(xx,yy,zz)
  33. X=X.transpose(1,0,2)
  34. Y=Y.transpose(1,0,2)
  35. Z=Z.transpose(1,0,2)
  36. if align_station:
  37. station_df['x(km)'] = station_df['x(km)'].apply(lambda x: xx[np.argmin(np.abs(np.array(xx) - x))])
  38. station_df['y(km)'] = station_df['y(km)'].apply(lambda x: yy[np.argmin(np.abs(np.array(yy) - x))])
  39. station_df['z(km)'] = station_df['z(km)'].apply(lambda x: zz[np.argmin(np.abs(np.array(zz) - x))])
  41. station_locs=np.array([station_df['x(km)'],station_df['y(km)'],station_df['z(km)']]).T
  42. loc_src_x=station_locs[:,0]
  43. loc_src_y=station_locs[:,1]
  44. loc_src_z=station_locs[:,2]
  45. n_station=len(loc_src_x)
  46. n_wavespeed=len(V_list)
  47. travel_time = np.zeros((n_wavespeed,n_station,grid_size_x,grid_size_y,grid_size_z))
  48. for j in tqdm(range(n_wavespeed)):
  49. V=V_list[j]
  50. #V=np.ones_like(X)
  51. for i in range(n_station):
  52. phi = ((X-loc_src_x[i])**2+(Y-loc_src_y[i])**2+(Z-loc_src_z[i])**2)
  53. #print(np.min(phi))
  54. #phi=phi-np.min(phi)
  55. phi=phi-0.001
  56. try:
  57. tt= skfmm.travel_time(phi,V,order=2,dx=dx)
  58. except:
  59. tt = skfmm.travel_time(phi,V,order=1,dx=dx)
  60. travel_time[j,i,:,:,:]=tt
  61. return travel_time
  64. def compute_task(inputs):
  65. phi,V,dx=inputs
  66. result = skfmm.travel_time(phi,V,order=2,dx=dx).astype(dtype=np.float16)
  67. return result
  69. def get_traveling_time_multi_mp(V_list,station_df,config,dx=25,align_station=False):
  70. grid_size_x= int((config['x(km)'][1]-config['x(km)'][0])/dx+1)
  71. grid_size_y= int((config['y(km)'][1]-config['y(km)'][0])/dx+1)
  72. grid_size_z= int((config['z(km)'][1]-config['z(km)'][0])/dx+1)
  73. xx = np.linspace(config['x(km)'][0],config['x(km)'][1],grid_size_x)
  74. yy = np.linspace(config['y(km)'][0],config['y(km)'][1],grid_size_y)
  75. zz = np.linspace(config['z(km)'][0],config['z(km)'][1],grid_size_z)
  76. X, Y, Z = np.meshgrid(xx,yy,zz)
  77. X=X.transpose(1,0,2)
  78. Y=Y.transpose(1,0,2)
  79. Z=Z.transpose(1,0,2)
  81. if align_station:
  82. station_df['x(km)'] = station_df['x(km)'].apply(lambda x: xx[np.argmin(np.abs(np.array(xx) - x))])
  83. station_df['y(km)'] = station_df['y(km)'].apply(lambda x: yy[np.argmin(np.abs(np.array(yy) - x))])
  84. station_df['z(km)'] = station_df['z(km)'].apply(lambda x: zz[np.argmin(np.abs(np.array(zz) - x))])
  85. station_locs=np.array([station_df['x(km)'],station_df['y(km)'],station_df['z(km)']]).T
  86. loc_src_x=station_locs[:,0]
  87. loc_src_y=station_locs[:,1]
  88. loc_src_z=station_locs[:,2]
  89. n_station=len(loc_src_x)
  90. n_wavespeed=len(V_list)
  91. data_list=[]
  92. for j in tqdm(range(n_wavespeed)):
  93. V=V_list[j]
  94. #V=np.ones_like(X)
  95. for i in range(n_station):
  96. phi = ((X-loc_src_x[i])**2+(Y-loc_src_y[i])**2+(Z-loc_src_z[i])**2)
  97. #print(np.min(phi))
  98. #phi=phi-np.min(phi)
  99. phi=phi-0.001
  100. # try:
  101. # tt= skfmm.travel_time(phi,V,order=2,dx=dx)
  102. # except:
  103. # tt = skfmm.travel_time(phi,V,order=1,dx=dx)
  104. data_list.append((phi,V,dx))
  105. pool = multiprocessing.Pool()
  106. result_iter = pool.imap(compute_task, data_list)
  107. result_list = []
  108. for result in tqdm(result_iter, total=n_wavespeed*n_station):
  109. result_list.append(result)
  110. pool.close()
  111. pool.join()
  112. result_list=np.array(result_list).astype(np.float16).reshape(n_wavespeed,n_station,grid_size_x,grid_size_y,grid_size_z)
  113. return result_list
  115. def add_gaussian_pertubation(x,y,z,sx,sy,sz,A,grid_size):
  116. Y,X,Z = np.meshgrid(np.linspace(0,1,grid_size), np.linspace(0,1,grid_size),np.linspace(0,1,grid_size))
  117. temp=(X-x)**2/sx**2+(Y-y)**2/sy**2+(Z-z)**2/sz**2
  118. temp=np.exp(-temp/2)
  119. return A*temp/temp.max()
  124. def gen_station(n_station,config,seed=0):
  125. np.random.seed(seed)
  126. dx =config['dx(km)']
  127. grid_size_x= int((config['x(km)'][1]-config['x(km)'][0])/dx+1)
  128. grid_size_y= int((config['y(km)'][1]-config['y(km)'][0])/dx+1)
  129. grid_size_z= int((config['z(km)'][1]-config['z(km)'][0])/dx+1)
  130. x = np.linspace(config['x(km)'][0],config['x(km)'][1],grid_size_x)
  131. y = np.linspace(config['y(km)'][0],config['y(km)'][1],grid_size_y)
  132. z = np.linspace(config['z(km)'][0],config['z(km)'][1],grid_size_z)
  135. station_loc=[]
  136. for i in range(n_station):
  137. loc=[x[np.random.randint(len(x))],y[np.random.randint(len(y))],0.0]
  138. #loc=[x[2],y[18],0.0]
  139. station_loc.append(loc)
  140. station_df = []
  141. for i in range(n_station):
  142. loc=station_loc[i]
  143. station_df.append({
  144. "id": 'S.'+str(i)+'.BH',
  145. "x(km)": loc[0],
  146. "y(km)": loc[1],
  147. "z(km)": loc[2]
  148. })
  149. station_df=pd.DataFrame(station_df)
  151. return station_df
  153. def gen_source(n_source,frequence,config,seed=0,randomtime=False):
  154. np.random.seed(seed)
  155. source_loc=[]
  156. source_loc_lindex=[]
  157. source_time=[]
  159. dx =config['dx(km)']
  160. grid_size_x= int((config['x(km)'][1]-config['x(km)'][0])/dx+1)
  161. grid_size_y= int((config['y(km)'][1]-config['y(km)'][0])/dx+1)
  162. grid_size_z= int((config['z(km)'][1]-config['z(km)'][0])/dx+1)
  163. x = np.linspace(config['x(km)'][0],config['x(km)'][1],grid_size_x)
  164. y = np.linspace(config['y(km)'][0],config['y(km)'][1],grid_size_y)
  165. z = np.linspace(config['z(km)'][0],config['z(km)'][1],grid_size_z)
  167. Tmax=60/frequence*n_source
  168. if randomtime:
  169. Tlist=np.random.rand(n_source)*Tmax
  170. else:
  171. Tlist=np.linspace(0,Tmax,n_source)
  172. for n in range(n_source):
  173. #idxs=[np.random.randint(len(x)),np.random.randint(len(y)),np.random.randint(len(z))]
  174. idxs=[np.random.randint(1,len(x)-1),np.random.randint(1,len(y)-1),np.random.randint(11,len(z)-1)] #avoid boundary
  175. source_loc_lindex.append(idxs)
  176. source_loc.append([x[idxs[0]],y[idxs[1]],z[idxs[2]]])
  177. #source_time.append(np.random.rand()*60/frequence*8)
  178. source_time.append(Tlist[n])
  180. catalog_df=[]
  181. for source_index in range(n_source):
  182. loc=source_loc[source_index]
  183. catalog_df.append({
  184. "event_index": source_index,
  185. "time": np.datetime64(int(1000*source_time[source_index]), 'ms'),
  186. "x(km)": loc[0],
  187. "y(km)": loc[1],
  188. "z(km)": loc[2],
  189. })
  190. catalog_df=pd.DataFrame(catalog_df)
  191. catalog_df['time'] = catalog_df['time'].apply(lambda x: UT(x))
  195. return source_loc,source_loc_lindex,source_time,catalog_df
  198. import torch
  201. class TravelTimeDataset(Dataset):
  202. def __init__(self,travel_time_list,V_paramter_list,config,station_df):
  203. self.n_wavespeed=len(V_paramter_list)
  204. self.n_station=len(station_df)
  205. self.dx=config['dx(km)']
  206. self.input_scale=100
  207. self.out_scale=100
  208. grid_size_x= int((config['x(km)'][1]-config['x(km)'][0])/dx+1)
  209. grid_size_y= int((config['y(km)'][1]-config['y(km)'][0])/dx+1)
  210. grid_size_z= int((config['z(km)'][1]-config['z(km)'][0])/dx+1)
  211. x = np.linspace(config['x(km)'][0],config['x(km)'][1],grid_size_x)
  212. y = np.linspace(config['y(km)'][0],config['y(km)'][1],grid_size_y)
  213. z = np.linspace(config['z(km)'][0],config['z(km)'][1],grid_size_z)
  214. X, Y, Z = np.meshgrid(x,y,z)
  215. X=X.transpose(1,0,2)
  216. Y=Y.transpose(1,0,2)
  217. Z=Z.transpose(1,0,2)
  219. self.X =(X-config['x(km)'][0])/(config['x(km)'][1]-config['x(km)'][0])
  220. self.Y =(Y-config['y(km)'][0])/(config['y(km)'][1]-config['y(km)'][0])
  221. self.Z =(Z-config['z(km)'][0])/(config['z(km)'][1]-config['z(km)'][0])
  223. self.grid_sizes=[grid_size_x,grid_size_y,grid_size_z]
  224. self.travel_time_list=travel_time_list
  225. self.n_gt=grid_size_x*grid_size_y*grid_size_z
  226. self.V_paramter_list=V_paramter_list
  227. ##station
  228. print(self.X.shape,self.Y.shape,self.Z.shape)
  229. print(travel_time_list.shape)
  230. #self.station_locs=np.array([station_df['x(km)'],station_df['y(km)'],station_df['z(km)']])
  231. def __len__(self):
  232. return self.n_wavespeed*self.n_gt
  233. def __getitem__(self, idx):
  234. idx_wavespeed,id_= idx//self.n_gt,idx%self.n_gt
  235. idx,id_= id_//(self.grid_sizes[1]*self.grid_sizes[2]),id_%(self.grid_sizes[1]*self.grid_sizes[2])
  236. idy,idz= id_//self.grid_sizes[2],id_%self.grid_sizes[2]
  237. input=np.concatenate([self.V_paramter_list[idx_wavespeed], [self.X[idx,idy,idz]], [self.Y[idx,idy,idz]],[self.Z[idx,idy,idz]]])
  238. output=self.travel_time_list[idx_wavespeed,:,idx,idy,idz]
  239. image = {'in':input,'out':output}
  240. return image
  247. class TravelTimeDataset_NF(Dataset):
  248. def __init__(self,travel_time_list,WaveSpeedData,p_list,model_autoencoder,device,config,beta=0):
  249. self.n_wavespeed=len(WaveSpeedData)
  250. self.dx=config['dx(km)']
  251. dx=self.dx
  252. self.beta=beta
  253. #ATE_train_loader = torch.utils.data.DataLoader(WaveSpeedData, batch_size=128, shuffle=False)
  254. model_autoencoder.eval()
  255. with torch.no_grad():
  256. data=torch.tensor(WaveSpeedData.data_wavespeed).unsqueeze(1).float().to(device)
  257. _,emb=model_autoencoder(data)
  258. p=emb.clone().detach().cpu().squeeze()
  259. self.z=torch.sigmoid(self.beta*p).numpy()
  260. self.p_list=p_list
  261. if self.z.ndim == 1:
  262. self.z = np.expand_dims(self.z, axis=-1)
  263. print('z,',self.z[:5])
  266. grid_size_x= int((config['x(km)'][1]-config['x(km)'][0])/dx+1)
  267. grid_size_y= int((config['y(km)'][1]-config['y(km)'][0])/dx+1)
  268. grid_size_z= int((config['z(km)'][1]-config['z(km)'][0])/dx+1)
  269. x = np.linspace(config['x(km)'][0],config['x(km)'][1],grid_size_x)
  270. y = np.linspace(config['y(km)'][0],config['y(km)'][1],grid_size_y)
  271. z = np.linspace(config['z(km)'][0],config['z(km)'][1],grid_size_z)
  272. X, Y, Z = np.meshgrid(x,y,z)
  273. X=X.transpose(1,0,2)
  274. Y=Y.transpose(1,0,2)
  275. Z=Z.transpose(1,0,2)
  277. self.X =(X-config['x(km)'][0])/(config['x(km)'][1]-config['x(km)'][0])
  278. self.Y =(Y-config['y(km)'][0])/(config['y(km)'][1]-config['y(km)'][0])
  279. self.Z =(Z-config['z(km)'][0])/(config['z(km)'][1]-config['z(km)'][0])
  281. self.grid_sizes=[grid_size_x,grid_size_y,grid_size_z]
  282. self.travel_time_list=travel_time_list
  283. self.n_gt=grid_size_x*grid_size_y*grid_size_z
  284. #self.V_paramter_list=V_paramter_list
  285. ##station
  286. print(self.X.shape,self.Y.shape,self.Z.shape)
  287. print(travel_time_list.shape)
  288. #self.station_locs=np.array([station_df['x(km)'],station_df['y(km)'],station_df['z(km)']])
  289. def __len__(self):
  290. return self.n_wavespeed*self.n_gt
  291. def __getitem__(self, idx):
  292. idx_wavespeed,id_= idx//self.n_gt,idx%self.n_gt
  293. idx,id_= id_//(self.grid_sizes[1]*self.grid_sizes[2]),id_%(self.grid_sizes[1]*self.grid_sizes[2])
  294. idy,idz= id_//self.grid_sizes[2],id_%self.grid_sizes[2]
  295. input=np.concatenate([self.z[idx_wavespeed], [self.X[idx,idy,idz]], [self.Y[idx,idy,idz]],[self.Z[idx,idy,idz]]])
  296. output=self.travel_time_list[idx_wavespeed,:,idx,idy,idz]
  297. p=self.p_list[idx_wavespeed]
  298. image = {'in':input,'out':output,'p':p}
  299. return image

NF_utils.py at commit 7adf666, under MIT · at the source

Overview

Authors: Cheng Shi1,2, Giulio Poggiali3, Chris Marone3,4, Maarten V. de Hoop5, Ivan Dokmanić1,6
ORCID iDs: Cheng Shi, Giulio Poggiali
  1. Department of Mathematics and Computer Science, University of Basel,Basel, Switzerland
  2. Département d’Informatique, École normale supérieure, PSL University,Paris, France
  3. Department of Earth Sciences, La Sapienza Università di Roma,Roma, Italy
  4. Department of Geosciences, Pennsylvania State University,University Park, PA USA
  5. Simons Chair in Computational and Applied Mathematics and Earth Science, Rice University,Houston, TX USA
  6. Department of ECE, University of Illinois at Urbana–Champaign,Champaign, IL USA
Institutions: University of Basel (Switzerland); Université Paris Sciences et Lettres (France); Sapienza University of Rome (Italy); Pennsylvania State University (United States); Rice University (United States); University of Illinois Urbana-Champaign (United States)
Journal: Nature communications, volume 17, issue 1, article 8140
Dates: received 15 March 2024; accepted 27 May 2026; published online 30 June 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41467-026-74092-y · PMID 42380143 · PMCID PMC13457860 · OpenAlex W7166663565
Open access: gold, a free copy (OpenAlex)
Status: code verified
Methods: Statistics, Machine learning
Keywords: Seismology, Computer science
Topic: Seismology and Earthquake Studies (Artificial Intelligence, Computer Science), according to OpenAlex
Funding: Simons Foundation under the MATH+X program, and Department of Energy, grant DE-SC0020345; European Research Council (ERC) Starting Grant 852821—SWING
Citations: cited by 1 paper (Europe PMC); 56 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repositories

Its files are read in the Code ↔ Paper reader above.

DaDaCheng/phase_association

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 7adf66667eee66a2d5e34ceb47df584dba8ad1d2, 1 September 2026
Languages: Python (9)
Size: 12 files, 9 scripts
Software Heritage: not archived
Found in: “Code availability”
Holds: README, license file, environment (setup.py)
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: NumPy (5 files), PyTorch (5 files), pandas (4 files), SciPy (2 files), Matplotlib (1 file), Plotly (1 file), scikit-learn (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
11 files
At the source: github.com/DaDaCheng/phase_association

Zenodo 19766525

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: “Code availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (5 files), PyTorch (5 files), pandas (4 files), SciPy (2 files), Matplotlib (1 file), Plotly (1 file), scikit-learn (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)
  • 27 September 2026: the link answers (HTTP 200)
11 files
At the source:

Code availability statement

The paper has a code availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41467-026-74092-y.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 18 scripts, each with its path and the digest of its content;
  • no match between paragraphs and code yet;
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Code and data availability statement

The paper has a code and data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41467-026-74092-y.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 2 keywords, 2 funders, 29 references.

Cite

This paper

Shi, C., Poggiali, G., Marone, C., de Hoop, M. V., & Dokmanić, I. (2026). High-rate phase association with travel time neural fields. Nature communications, 17(1), 8140. https://doi.org/10.1038/s41467-026-74092-y

BibTeX

@article{shi2026high,
author = {Shi, Cheng and Poggiali, Giulio and Marone, Chris and de Hoop, Maarten V. and Dokmanić, Ivan},
title = {{High-rate phase association with travel time neural fields}},
journal = {Nature communications},
year = {2026},
month = jun,
volume = {17},
number = {1},
pages = {8140},
publisher = {Nature Publishing Group},
issn = {2041-1723},
doi = {10.1038/s41467-026-74092-y},
url = {https://doi.org/10.1038/s41467-026-74092-y},
pmid = {42380143},
pmcid = {PMC13457860}
}

RIS

TY - JOUR
AU - Shi, Cheng
AU - Poggiali, Giulio
AU - Marone, Chris
AU - de Hoop, Maarten V.
AU - Dokmanić, Ivan
TI - High-rate phase association with travel time neural fields
T2 - Nature communications
J2 - Nat Commun
PY - 2026
DA - 2026/06/30
VL - 17
IS - 1
SP - 8140
SN - 2041-1723
PB - Nature Publishing Group
DO - 10.1038/s41467-026-74092-y
UR - https://doi.org/10.1038/s41467-026-74092-y
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41467-026-74092-y",
"type": "article-journal",
"title": "High-rate phase association with travel time neural fields",
"container-title": "Nature communications",
"author": [
{
"family": "Shi",
"given": "Cheng"
},
{
"family": "Poggiali",
"given": "Giulio"
},
{
"family": "Marone",
"given": "Chris"
},
{
"family": "de Hoop",
"given": "Maarten V."
},
{
"family": "Dokmanić",
"given": "Ivan"
}
],
"container-title-short": "Nat Commun",
"volume": "17",
"issue": "1",
"page": "8140",
"DOI": "10.1038/s41467-026-74092-y",
"PMID": "42380143",
"PMCID": "PMC13457860",
"ISSN": "2041-1723",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41467-026-74092-y",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
30
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[2] doi:10.3390/bioengineering13080924 [code]
Deep Learning-Based Temporal Gait Analysis Using a Smartphone IMU in Older Adults with and Without Non-Specific Low Back Pain.
Journal: Bioengineering (Basel, Switzerland)
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[3] doi:10.1016/j.isci.2026.116900 [code]
Dog brain representations of human facial expressions: Encoding happiness and differentiating specific negative expressions.
Journal: iScience
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[4] doi:10.1038/s41593-026-02388-9 [code]
Hippocampal CA3 connectomics reveals a gradient of mossy fiber inputs and selective feedforward inhibition onto pyramidal cells.
Journal: Nature neuroscience
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[5] doi:10.1002/hbm.70600 [code]
A Data-Driven Closed-Loop Control Approach to Drive Neural State Transitions for Mechanistic Insight.
Journal: Human brain mapping
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[6] doi:10.1126/sciadv.adz6517 [code]
Corticosterone-linked microglial activity underpins sexually dimorphic neuroplasticity after ketamine anesthesia.
Journal: Science advances
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[7] doi:10.1016/j.xcrm.2026.102943 [code]
Parent-of-origin effects in Alzheimer's liability dissociate neurocognitive and cardiovascular traits in at-risk individuals.
Journal: Cell reports. Medicine
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[8] doi:10.1016/j.isci.2026.116825 [code]
Social hierarchy shapes behavioral and transcriptional responses to chronic stress and ketamine in male mice.
Journal: iScience
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[9] doi:10.1038/s41467-026-75455-1 [code]
Shared latent representations of speech production for cross-patient speech decoding.
Journal: Nature communications
In common: Plotly, PyTorch, scikit-learn, 4 other tools
[10] doi:10.7554/elife.110074 [code]
Disentangling cephalopod chromatophores motor units with computer vision.
Journal: eLife
In common: Plotly, PyTorch, scikit-learn, 4 other tools

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.