Dynamic spatiotemporal features in action recognition: a multimodal study.
7 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.
The 12 matches
- [1] § Methods › Action classification of the two-stream CNNs and the layer features ↔ figure_data_and_scripts.zip/fig_s2_script/plot_fig_s2_i3d_k400.py, lines 25 to 97 · score 0.92 · backbone.layer1.2.relu, backbone.layer2.3.relu, backbone.layer3.5.relu, backbone.layer4.2.relu, backbone.maxpool, cls_head.dropout · block
oscr:b:5BQRZ51RFACGH-V· Report a mismatch - [2] § Methods › Action classification of the two-stream CNNs and the layer features ↔ figure_data_and_scripts.zip/fig_s2_script/plot_fig_s2_tsn_k400.py, lines 27 to 101 · score 0.92 · backbone.layer1.2.relu, backbone.layer2.3.relu, backbone.layer3.5.relu, backbone.layer4.2.relu, backbone.maxpool, cls_head.dropout · block
oscr:b:EXXA66NVWZWA0-I· Report a mismatch - [3] § Results › Dynamic spatial and temporal features and feature distance ↔ figure_data_and_scripts.zip/fig_s3_s4_data_script/plot_baseline_for_table4_exampleCode.m, lines 8 to 38 · score 0.78 · movement velocity, motion energy, movement direction, Hu moments, arm, HOF · block
oscr:b:VWJM9MGBYPTFP-Q· Report a mismatch - [4] § Methods › Estimation of dynamic spatial and temporal features ↔ figure_data_and_scripts.zip/fig_4_script/fig_4_script.py, lines 78 to 118 · score 0.77 · movement velocity, Motion energy, Movement direction, temporal features, HOF, segmentation · block
oscr:b:XSM6CH8CX150F-V· Report a mismatch - [5] § Methods › Estimation of dynamic spatial and temporal features ↔ figure_data_and_scripts.zip/fig_s3_s4_data_script/plot_baseline_for_table4_exampleCode.m, lines 8 to 38 · score 0.72 · movement velocity, Motion energy, Movement direction, HOF, HOG, silhouettes · block
oscr:b:VWJM9MGBYPTFP-Q· Report a mismatch - [6] § Results › Dynamic spatial and temporal features and feature distance ↔ figure_data_and_scripts.zip/fig_4_script/fig_4_script.py, lines 78 to 118 · score 0.71 · movement velocity, motion energy, movement direction, temporal features, HOF, flow · block
oscr:b:XSM6CH8CX150F-V· Report a mismatch - [7] § Methods › Action classification of the two-stream CNNs and the layer features ↔ figure_data_and_scripts.zip/fig_s2_script/plot_fig_s2_tsn_ssv2.py, lines 26 to 98 · score 0.66 · TSN SSV2, I3D K400, epoch, permutation, baseline, models · block
oscr:b:9DA2J8BS9PAH8-A· Report a mismatch - [8] § Methods › Action classification of the two-stream CNNs and the layer features ↔ figure_data_and_scripts.zip/fig_s2_script/plot_fig_s2_i3d_k400.py, lines 25 to 97 · score 0.66 · I3D K400, TSN SSV2, epoch, permutation, baseline, models · block
oscr:b:5BQRZ51RFACGH-V· Report a mismatch - [9] § Results › Dynamic spatial and temporal features and feature distance ↔ figure_data_and_scripts.zip/fig_s2_script/plot_fig_s2_tsn_k400.py, lines 27 to 101 · score 0.61 · TSN K400, I3D K400, TSN SSV2, layers, distance, videos · block
oscr:b:EXXA66NVWZWA0-I· Report a mismatch - [10] § Results › Dynamic spatial and temporal features and feature distance ↔ figure_data_and_scripts.zip/fig_s2_script/plot_fig_s2_tsn_ssv2.py, lines 26 to 98 · score 0.61 · TSN SSV2, TSN K400, I3D K400, layers, distance, videos · block
oscr:b:9DA2J8BS9PAH8-A· Report a mismatch - [11] § Methods › Multivariate ROI-based decoding ↔ figure_data_and_scripts.zip/fig_1_script/MVPA_exampleCode.m, lines 44 to 60 · score 0.53 · hand static, hand grasp, MVPA, maps · block
oscr:b:T1BA58Q5Y04MC-T· Report a mismatch - [12] § Methods › Correlation between behavioral performance and stimulus features ↔ figure_data_and_scripts.zip/fig_2_script/plot_fig_2b.py, lines 21 to 44 · score 0.51 · behavioral bias, confusion matrices, touching, monkeys · block
oscr:b:Q505BY19EZJTR-X· Report a mismatch
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 153 lines · 7.3 KB · CC-BY-4.0 · 2 matches
- import numpy as np
- from matplotlib import pyplot as plt
- import os
- import copy
- import json
- from json import JSONEncoder
- from scipy.stats import permutation_test
- from scipy.spatial.distance import cosine
- class NumpyArrayEncoder(JSONEncoder):
- def default(self, obj):
- if isinstance(obj, np.ndarray):
- return obj.tolist()
- return JSONEncoder.default(self, obj)
- def stat_cosine(x, y, normalize=False):
- x_to_compare = copy.deepcopy(x)
- y_to_compare = copy.deepcopy(y)
- if normalize:
- x_to_compare = (x_to_compare - np.min(x_to_compare)) / (np.max(x_to_compare) - np.min(x_to_compare))
- y_to_compare = (y_to_compare - np.min(y_to_compare)) / (np.max(y_to_compare) - np.min(y_to_compare))
- return 1 - cosine(x_to_compare, y_to_compare)
- # Load data
- M1_behavior_index_dist_file = 'M1_behavior_index_distmap.json'
- M2_behavior_index_dist_file = 'M2_behavior_index_distmap.json'
- Group_behavior_index_dist_file = 'Group_behavior_index_distmap.json'
- with open(M1_behavior_index_dist_file, "r") as infile:
- M1_behavior_index_distmap = json.load(infile)
- with open(M2_behavior_index_dist_file, "r") as infile:
- M2_behavior_index_distmap = json.load(infile)
- with open(Group_behavior_index_dist_file, "r") as infile:
- Group_behavior_index_distmap = json.load(infile)
- update_data = False
- selected_layer_list = [
- 'backbone.maxpool',
- 'backbone.layer1.2.relu',
- 'backbone.layer2.3.relu',
- 'backbone.layer3.5.relu',
- 'backbone.layer4.2.relu',
- 'cls_head.dropout',
- ]
- labels = ['grasp', 'touch', 'reach']
- root_dir = 'i3d_k400_mean-epoch_150-nonzero'
- data_dir = os.path.join(root_dir, 'layers')
- output_dir = os.path.join(root_dir, 'figs')
- video_name_list = [
- 'green', 'small', 'ring', 'flip', 'right_hand', 'actorL', 'actorT', 'monkey_hand', 'monkey_tail',
- ]
- if update_data:
- model_vector_dict = {}
- comparison_results = {}
- for layer_name in selected_layer_list:
- # Check if chd_vector-{layer_name.replace(".", "_")}.json exists
- if os.path.exists(os.path.join(data_dir, f'chd_vector-{layer_name.replace(".", "_")}.json')):
- model_vector = json.load(open(os.path.join(data_dir, f'chd_vector-{layer_name.replace(".", "_")}.json'), "r"))
- else:
- model_vector = []
- for video_name in video_name_list:
- layer_dist_file = os.path.join(data_dir, f'chd_vector-{video_name}-{layer_name.replace(".", "_")}.json')
- model_vector.extend(json.load(open(layer_dist_file, "r"))['dist_vector'])
- model_vector_dict[layer_name] = model_vector
- M1_vector = M1_behavior_index_distmap['index_vector']
- M2_vector = M2_behavior_index_distmap['index_vector']
- Group_vector = Group_behavior_index_distmap['index_vector']
- # Calculate cosine similarity
- M1_cosine_perm = permutation_test((model_vector, M1_vector), stat_cosine, permutation_type='independent', vectorized=False, n_resamples=100000, alternative='greater')
- M2_cosine_perm = permutation_test((model_vector, M2_vector), stat_cosine, permutation_type='independent', vectorized=False, n_resamples=100000, alternative='greater')
- Group_cosine_perm = permutation_test((model_vector, Group_vector), stat_cosine, permutation_type='independent', vectorized=False, n_resamples=100000, alternative='greater')
- M1_cosine = M1_cosine_perm.statistic
- M1_pvalue = M1_cosine_perm.pvalue
- M1_baseline = M1_cosine_perm.null_distribution.mean()
- M2_cosine = M2_cosine_perm.statistic
- M2_pvalue = M2_cosine_perm.pvalue
- M2_baseline = M2_cosine_perm.null_distribution.mean()
- Group_cosine = Group_cosine_perm.statistic
- Group_pvalue = Group_cosine_perm.pvalue
- Group_baseline = Group_cosine_perm.null_distribution.mean()
- comparison_results[layer_name] = {
- 'M1': {'cosine': M1_cosine, 'pvalue': M1_pvalue, 'baseline': M1_baseline},
- 'M2': {'cosine': M2_cosine, 'pvalue': M2_pvalue, 'baseline': M2_baseline},
- 'Group': {'cosine': Group_cosine, 'pvalue': Group_pvalue, 'baseline': Group_baseline},
- }
- # Change keys to ['I3D_K400', 'TSN_K400', 'TSN_SSV2']
- # Save data to json
- with open(os.path.join(output_dir, 'layer_dist_dict-i3d_k400_mean-epoch_150-nonzero.json'), "w") as outfile:
- json.dump(model_vector_dict, outfile, cls=NumpyArrayEncoder, indent=4)
- with open(os.path.join(output_dir, 'comparison_results-i3d_k400_mean-epoch_150-nonzero.json'), "w") as outfile:
- json.dump(comparison_results, outfile, cls=NumpyArrayEncoder, indent=4)
- else:
- layer_dist_dict = json.load(open(os.path.join(output_dir, 'layer_dist_dict-i3d_k400_mean-epoch_150-nonzero.json'), "r"))
- comparison_results = json.load(open(os.path.join(output_dir, 'comparison_results-i3d_k400_mean-epoch_150-nonzero.json'), "r"))
- # Plot results
- ann_list = []
- ann_cos_group = []
- ann_pvalue_group = []
- ann_baseline_group = []
- ann_cos_m1 = []
- ann_pvalue_m1 = []
- ann_baseline_m1 = []
- ann_cos_m2 = []
- ann_pvalue_m2 = []
- ann_baseline_m2 = []
- for layer_name in selected_layer_list:
- ann_list.append(layer_name)
- ann_cos_group.append(comparison_results[layer_name]['Group']['cosine'])
- ann_pvalue_group.append(comparison_results[layer_name]['Group']['pvalue'])
- ann_baseline_group.append(comparison_results[layer_name]['Group']['baseline'])
- ann_cos_m1.append(comparison_results[layer_name]['M1']['cosine'])
- ann_pvalue_m1.append(comparison_results[layer_name]['M1']['pvalue'])
- ann_baseline_m1.append(comparison_results[layer_name]['M1']['baseline'])
- ann_cos_m2.append(comparison_results[layer_name]['M2']['cosine'])
- ann_pvalue_m2.append(comparison_results[layer_name]['M2']['pvalue'])
- ann_baseline_m2.append(comparison_results[layer_name]['M2']['baseline'])
- fig, ax = plt.subplots(1, 1, figsize=(10, 8))
- bp = ax.bar(ann_list, ann_cos_group, width=0.75)
- # bar color
- for i, bar in enumerate(bp):
- if ann_pvalue_group[i] < 0.05:
- # Only edge color, no fill
- bar.set_edgecolor('red')
- bar.set_facecolor('none')
- else:
- bar.set_edgecolor('black')
- bar.set_facecolor('none')
- # Add a short baseline dashed line with x spanning bar left - 0.05 to bar right + 0.05)
- ax.plot([bar.get_x() - 0.05, bar.get_x() + 0.8], [ann_baseline_group[i], ann_baseline_group[i]], color='black', linestyle='--', linewidth=1)
- for i, x in enumerate(ann_cos_m1):
- if ann_pvalue_m1[i] < 0.05:
- ax.scatter(i, x, marker='o', s=50, edgecolor='red', facecolor='none')
- else:
- ax.scatter(i, x, marker='o', s=50, edgecolor='black', facecolor='none')
- for i, x in enumerate(ann_cos_m2):
- if ann_pvalue_m2[i] < 0.05:
- ax.scatter(i, x, marker='^', s=50, edgecolor='red', facecolor='none')
- else:
- ax.scatter(i, x, marker='^', s=50, edgecolor='black', facecolor='none')
- ax.set_xticks([i for i in range(len(ann_list))])
- ax.set_xticklabels(ann_list, rotation=30)
- ax.set_xlabel('ANN layers')
- ax.set_ylabel('Cosine similarity')
- ax.set_ylim(0, 1)
- ax.set_title('I3D-K400 v.s. monkey behavior pattern similarity')
- plt.tight_layout()
- plt.savefig(os.path.join(output_dir, 'i3d_k400_mean-epoch_150-nonzero-monkey_behavior-pattern_comparison-selected_layers.png'))
- plt.savefig(os.path.join(output_dir, 'i3d_k400_mean-epoch_150-nonzero-monkey_behavior-pattern_comparison-selected_layers.pdf'), format='pdf', dpi=300)
- plt.close()
plot_fig_s2_i3d_k400.py, under CC-BY-4.0 · at the source
Overview
- Laboratory for Neuro- and Psychophysiology, Department of Neurosciences, KU Leuven, Leuven, Belgium
- Leuven Brain Institute, KU Leuven, Leuven, Belgium
Abstract
Recognizing and distinguishing actions is a complex cognitive process that relies on integrating various spatiotemporal information. However, the specific contributions of spatial and temporal features to action recognition remain unclear. To address this gap, we conducted fMRI recordings in monkeys as they observed videos of grasping, touching, and reaching actions. Using multivariate pattern analysis (MVPA), we identified distinct action representation patterns across the brain, with most regions of the action observation network (AON) exhibiting a grasping-dominant pattern. This neural representation was consistent with the monkeys’ behavioral differentiation of these actions in subsequent categorization tasks. Building on computer vision approaches, we systematically extracted dynamic spatial and temporal features from action videos, capturing evolution of feature information over time, and compared these features with the monkeys’ behavioral performance. Our results demonstrate that these features are utilized across a hierarchy and selectively correlate with behavior, reflecting a complex interplay between feature information and key action components. These findings imply a distributed coding strategy in which diverse spatial and temporal features are selectively integrated to form action representations that facilitate recognition or discrimination. Our study provides empirical evidence for current action recognition models and introduces advanced computational tools for analyzing high-dimensional and multimodal data.
Reproduced under the paper's license (CC BY), from the paper cited above.
Repository
Its files are read in the Code ↔ Paper reader above, with 12 matches between paragraphs and lines of code.
Zenodo 18978813
Availability: 1 check, the latest on 28 September 2026: the link answers (HTTP 200)
- 28 September 2026: the link answers (HTTP 200)
11 files
- figure_data_and_scripts.
zip/ , MATLAB, 305 lines, 1 matchfig_1_script/ MVPA_exampleCode.m - figure_data_and_scripts.
zip/ , Python, 67 linesfig_1_script/ plot_fig_1b.py - figure_data_and_scripts.
zip/ , Python, 72 lines, 1 matchfig_2_script/ plot_fig_2b.py - figure_data_and_scripts.
zip/ , Python, 52 linesfig_2_script/ plot_fig_2d.py - figure_data_and_scripts.
zip/ , Python, 201 lines, 2 matchesfig_4_script/ fig_4_script.py - figure_data_and_scripts.
zip/ , Python, 110 linesfig_s1_script/ fig_s1_script.py - figure_data_and_scripts.
zip/ , Python, 153 lines, 2 matchesfig_s2_script/ plot_fig_s2_i3d_k400.py - figure_data_and_scripts.
zip/ , Python, 157 lines, 2 matchesfig_s2_script/ plot_fig_s2_tsn_k400.py - figure_data_and_scripts.
zip/ , Python, 154 lines, 2 matchesfig_s2_script/ plot_fig_s2_tsn_ssv2.py - figure_data_and_scripts.
zip/ , MATLAB, 201 lines, 2 matchesfig_s3_s4_data_script/ plot_baseline_for_table4 _exampleCode.m - README.md, Text, 30 lines
Code availability
The code that supports the findings of this study is available online on Zenodo: 10.5281/
Reproduced under the paper's license (CC BY), from the paper cited above.
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:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 10 scripts, each with its path and the digest of its content;
- 12 matches between paragraphs of the paper and lines of the code (method lexical-v1);
- 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.
Data availability
The data that support the findings of this study are partially available online on Zenodo: 10.5281/
Reproduced under the paper's license (CC BY), from the paper cited above.
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, 28 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 2 keywords, 6 MeSH terms, 2 funders, 51 references.
Cite
This paper
Jin, Q., Cui, D., & Nelissen, K. (2026). Dynamic spatiotemporal features in action recognition: a multimodal study. Communications biology, 9(1), 734. https://
BibTeX
@article{jin2026dynamic,
author = {Jin, Qiuhan and Cui, Ding and Nelissen, Koen},
title = {{Dynamic spatiotemporal features in action recognition: a multimodal study}},
journal = {Communications biology},
year = {2026},
month = apr,
volume = {9},
number = {1},
pages = {734},
publisher = {Nature Portfolio},
issn = {2399-3642},
doi = {10.1038/
url = {https://
pmid = {41933034},
pmcid = {PMC13219507}
}
RIS
TY - JOUR
AU - Jin, Qiuhan
AU - Cui, Ding
AU - Nelissen, Koen
TI - Dynamic spatiotemporal features in action recognition: a multimodal study
T2 - Communications biology
J2 - Commun Biol
PY - 2026
DA - 2026/
VL - 9
IS - 1
SP - 734
SN - 2399-3642
PB - Nature Portfolio
DO - 10.1038/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1038/
"type": "article-journal",
"title": "Dynamic spatiotemporal features in action recognition: a multimodal study",
"container-title": "Communications biology",
"author": [
{
"family": "Jin",
"given": "Qiuhan"
},
{
"family": "Cui",
"given": "Ding"
},
{
"family": "Nelissen",
"given": "Koen"
}
],
"container-title-short":
"volume": "9",
"issue": "1",
"page": "734",
"DOI": "10.1038/
"PMID": "41933034",
"PMCID": "PMC13219507",
"ISSN": "2399-3642",
"publisher": "Nature Portfolio",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
3
]
]
}
}
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:10.1016/j.celrep.2023.113438 [code]
- Bodies in motion: Unraveling the distinct roles of motion and shape in dynamic body responses in the temporal cortex.Journal: Cell reportsIn common: OpenCV, pandas, SciPy, 2 other tools, non-human primate, cognitive, 6 references
- [2] doi:10.1038/s42003-026-09834-1 [code]
- Distinct perceptual and conceptual representations of natural actions along the lateral and dorsal visual streams.Journal: Communications biologyIn common: cognitive, 8 references
- [3] doi:10.1007/s00429-025-03042-z [code]
- Top-down modulation of visual action perception: distinct task effects in the action observation network.Journal: Brain structure & functionIn common: Statistics and Machine Learning Toolbox, pandas, Matplotlib, 1 other tool, cognitive, 6 references
- [4] doi:10.1038/s42003-023-04942-8 [code]
- Ultra-high field fMRI identifies an action-observation network in the common marmoset.Journal: Communications biologyIn common: non-human primate, 7 references
- [5] doi:10.1016/j.neuroimage.2023.119907
- The contribution of dynamics to macaque body and face patch responses.Journal: NeuroImageIn common: non-human primate, 7 references
- [6] doi:10.1162/imag.a.1019 [code]
- The spatiotemporal neural dynamics of action-related features underlying action recognition.Journal: Imaging neuroscience (Cambridge, Mass.)In common: Parallel Computing Toolbox, Statistics and Machine Learning Toolbox, 5 references
- [7] doi:10.1007/s00429-026-03111-x [code]
- Direction selectivity in naturalistic action observation: distributed representations across the action observation network.Journal: Brain structure & functionIn common: SPM, Statistics and Machine Learning Toolbox, 5 references
- [8] doi:10.7554/elife.75027 [code]
- Social-affective features drive human representations of observed actions.Journal: eLifeIn common: Statistics and Machine Learning Toolbox, pandas, Matplotlib, 1 other tool, cognitive, 4 references
- [9] doi:10.1038/s41467-024-50310-3 [code]
- Modeling short visual events through the BOLD moments video fMRI dataset and metadata.Journal: Nature communicationsIn common: pandas, SciPy, Matplotlib, 1 other tool, cognitive, 4 references
- [10] doi:10.1162/imag.a.1207 [code]
- Investigating the temporal dynamics and modeling of mid-level feature representations in humans.Journal: Imaging neuroscience (Cambridge, Mass.)In common: OpenCV, pandas, SciPy, 2 other tools, cognitive, 3 references
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.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 10 scripts, and 12 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:fd0e6d7474769e3a…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.1038/s42003-026-09917-z)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1038/s42003-026-09917-z.svg
:target: https://openscicode.org/badge/doi/10.1038/s42003-026-09917-z
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s42003-026-09917-z"><img src="https://openscicode.org/badge/doi/10.1038/s42003-026-09917-z.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge 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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
