OSCR

Evaluation of a Hybrid Neural-Polynomial Deep Q-Network for Switching-Aware Spectrum Selection in a Controlled Radio-Frequency Measurement-Replay Testbed.

Code ↔ Paper

40 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 40 matches
  1. [1] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ paper_aligned_results_and_audit/analysis/scripts/plot_revision_results.py, lines 890–939 · score 0.97 · frozen scan stratified, seed confidence intervals, occur twice, error bars, transfer scans, Pilot scans
  2. [2] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ paper_aligned_results_and_audit/analysis/scripts/plot_revision_results.py, lines 890–939 · score 0.96 · cross configuration evaluations, horizontal bars, Predeclared primary paired, comparison primary family, HNP DQN minus, paired training seeds
  3. [3] § 4. Experiments and Results Analysis › 4.6. Post Hoc Analysis of Expanded-Feature Weights ↔ paper_aligned_results_and_audit/analysis/scripts/audit_polynomial_branch_weights.py, lines 1–47 · score 0.93 · branch weights, descriptive raw weight, upstream activation scales, polynomial branch, descriptive audit, ignores activation frequency
  4. [4] § 3. HNP-DQN Architecture › 3.2. Capacity-Matched Conventional Control ↔ experiment_v2/src/models.py, lines 120–181 · score 0.85 · BatchNorm, hidden widths, ReLU, matched MLP DDQN, dueling head, HNP DQN
  5. [5] § 3. HNP-DQN Architecture › 3.2. Capacity-Matched Conventional Control ↔ experiment_v2/src/models.py, lines 120–181 · score 0.84 · post expansion, hidden widths, dueling head, LayerNorm, capacity matched, causal
  6. [6] § 4. Experiments and Results Analysis › 4.6. Post Hoc Analysis of Expanded-Feature Weights ↔ paper_aligned_results_and_audit/analysis/scripts/audit_polynomial_branch_weights.py, lines 326–376 · score 0.82 · absolute outgoing weight, squared minus linear, Frobenius norms, branch, jammer mode, audited
  7. [7] § 4. Experiments and Results Analysis › 4.4. Model Capacity and Computational Cost ↔ experiment_v2/src/runner.py, lines 394–411 · score 0.82 · temporary workspaces, excludes activations, Persistent tensor, registered buffers, optimizer state, allocator
  8. [8] § 4. Experiments and Results Analysis › 4.2. Endpoints and Statistical Analysis ↔ paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py, lines 1305–1359 · score 0.81 · predeclared primary family, exploratory Holm family, flip enumeration, fixed evaluation trajectories, paired training seeds, Holm correction
  9. [9] § 2. Dataset and Environment Modeling › 2.4. Agent Observation Representation ↔ experiment_v2/src/baselines.py, lines 1–24 · score 0.81 · jammer aware greedy, schedule aware sweep, ordinary observation, phase, baselines, oracle
  10. [10] § 2. Dataset and Environment Modeling › 2.1. RF Jamming Dataset ↔ experiment_v2/audit_data.py, lines 75–152 · score 0.79 · distance shift, power shift, Scan IDs, audits, dBm, split
  11. [11] § 4. Experiments and Results Analysis › 4.2. Endpoints and Statistical Analysis ↔ paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py, lines 35–110 · score 0.79 · jammer aware greedy, clairvoyant oracle, capacity matched MLP, schedule aware, HNP DQN, hysteresis
  12. [12] § 4. Experiments and Results Analysis › 4.4. Model Capacity and Computational Cost ↔ experiment_v2/profile_model_costs.py, lines 10–68 · score 0.78 · allocator overhead, temporary workspaces, excludes activations, registered buffers, pacing, thread
  13. [13] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ experiment_v2/src/baselines.py, lines 255–297 · score 0.77 · preceding step, Schedule aware sweeping, safe channel, RF observation, swept, phase
  14. [14] § 3. HNP-DQN Architecture › 3.1. Proposed Architecture ↔ paper_aligned_results_and_audit/analysis/scripts/plot_hnp_architecture.py, lines 123–261 · score 0.77 · TD objective, ReLU, online network, target network, linear, expansion
  15. [15] § 4. Experiments and Results Analysis › 4.4. Model Capacity and Computational Cost ↔ paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py, lines 707–775 · score 0.74 · GPU inference, persistent tensor, serialized state, trainable parameters, repetition, memory
  16. [16] § 4. Experiments and Results Analysis › 4.2. Endpoints and Statistical Analysis ↔ paper_aligned_results_and_audit/analysis/scripts/build_revision_artifacts.py, lines 836–955 · score 0.73 · flip enumeration, Holm family, paired seed, Cohen, trained seed, jammer mode
  17. [17] § 3. HNP-DQN Architecture › 3.1. Proposed Architecture ↔ paper_aligned_results_and_audit/analysis/scripts/plot_hnp_architecture.py, lines 123–261 · score 0.73 · online network, Polyak update, target network, RF entries, MSE, concatenates
  18. [18] § 2. Dataset and Environment Modeling › 2.6. Reward Design and Performance Objectives ↔ experiment_v2/src/env.py, lines 281–331 · score 0.72 · successful retention, successful switch, switching cost, dominant, event, collision
  19. [19] § 4. Experiments and Results Analysis › 4.4. Model Capacity and Computational Cost ↔ experiment_v2/src/runner.py, lines 436–491 · score 0.72 · reports trainable parameters, persistent tensor, serialized state, GPU, latency, CPU
  20. [20] § 2. Dataset and Environment Modeling › 2.4. Agent Observation Representation ↔ paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py, lines 35–110 · score 0.72 · jammer aware greedy, schedule aware sweep, oracle, privileged, ordinary, clairvoyant
  21. [21] § 3. HNP-DQN Architecture › 3.1. Proposed Architecture ↔ paper_aligned_results_and_audit/analysis/scripts/map_manuscript_locations.py, lines 47–106 · score 0.71 · neural feature extractor, HNP DQN combines, channel encoding, RF summaries, LayerNorm, expansion
  22. [22] § 3. HNP-DQN Architecture › 3.4. Agent Training Procedure ↔ experiment_v2/src/runner.py, lines 161–226 · score 0.70 · terminal state, stored transition, absorbing, mask, truncation, bootstrap
  23. [23] § 2. Dataset and Environment Modeling › 2.6. Reward Design and Performance Objectives ↔ paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py, lines 1490–1549 · score 0.69 · Supporting endpoints, inferential unit, fixed trajectories, independently trained seed, family, Holm
  24. [24] § 2. Dataset and Environment Modeling › 2.1. RF Jamming Dataset ↔ paper_aligned_results_and_audit/analysis/scripts/plot_training_snr_direction.py, lines 1–25 · score 0.69 · maximum quality, snr field, minimum interference, raw, scan, training
  25. [25] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ paper_aligned_results_and_audit/analysis/scripts/map_manuscript_locations.py, lines 107–166 · score 0.67 · Cross model TD, loss magnitude, TD loss, bootstrap targets, polynomial mapping, LayerNorm
  26. [26] § 3. HNP-DQN Architecture › 3.4. Agent Training Procedure ↔ paper_aligned_results_and_audit/analysis/scripts/map_manuscript_locations.py, lines 167–201 · score 0.67 · absorbing environmental terminal, limit truncation, step boundary, terminal state, Agent, Training
  27. [27] § 4. Experiments and Results Analysis › 4.5. Ablation Study ↔ paper_aligned_results_and_audit/analysis/scripts/build_revision_artifacts.py, lines 1–44 · score 0.66 · exploratory Holm family, primary comparison family, full HNP, capacity matched, training seed, variant
  28. [28] § 2. Dataset and Environment Modeling › 2.1. RF Jamming Dataset ↔ paper_aligned_results_and_audit/analysis/scripts/plot_training_snr_direction.py, lines 1–25 · score 0.66 · fixed jammer source, snr field, Development training, audit, quality, pilot
  29. [29] § 3. HNP-DQN Architecture › 3.4. Agent Training Procedure ↔ agents/DQN_agents/HNP_DQN.py, lines 65–100 · score 0.66 · soft update, replay buffer, target network, greedy, optimize, batch
  30. [30] § 3. HNP-DQN Architecture › 3.4. Agent Training Procedure ↔ experiment_v2/src/agent.py, lines 372–409 · score 0.65 · soft update, online network, target network, optimize, batch, replay
  31. [31] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ experiment_v2/src/baselines.py, lines 1–24 · score 0.65 · Jammer aware greedy, upper bound, jammed channel, privileged, quality
  32. [32] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ experiment_v2/src/baselines.py, lines 356–467 · score 0.64 · dynamic programming, upper bound, switching cost, DP, Clairvoyant, horizon
  33. [33] § 3. HNP-DQN Architecture › 3.3. Training and Target-Update Procedure ↔ experiment_v2/src/agent.py, lines 372–409 · score 0.64 · online network selects, target network evaluates, prediction, gradient, Training
  34. [34] § 3. HNP-DQN Architecture › 3.1. Proposed Architecture ↔ experiment_v2/src/models.py, lines 58–118 · score 0.64 · polynomial expansion, LayerNorm, concatenates, hidden, module, heads
  35. [35] § 4. Experiments and Results Analysis › 4.4. Model Capacity and Computational Cost ↔ paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py, lines 1081–1152 · score 0.64 · serialized state, persistent parameter, KiB, median, engineering, HNP DQN
  36. [36] § 3. HNP-DQN Architecture › 3.3. Training and Target-Update Procedure ↔ agents/DQN_agents/DQN_With_Fixed_Q_Targets.py, lines 6–33 · score 0.60 · learning iteration, soft update, target network, Training
  37. [37] § 4. Experiments and Results Analysis › 4.1. Experimental Setup and Parameter Configuration ↔ paper_aligned_results_and_audit/analysis/scripts/map_manuscript_locations.py, lines 47–106 · score 0.60 · formal endpoint, scan stratified, learned policy, fixed trajectories, jammer mode, auditing
  38. [38] § 3. HNP-DQN Architecture › 3.1. Proposed Architecture › 3.1.2. Polynomial Mapping Layer ↔ experiment_v2/src/models.py, lines 58–118 · score 0.58 · polynomial basis, cross feature, expansion, squares, layer, dimensional
  39. [39] § 2. Dataset and Environment Modeling › 2.6. Reward Design and Performance Objectives ↔ paper_aligned_results_and_audit/analysis/scripts/map_manuscript_locations.py, lines 167–201 · score 0.57 · reward prioritizes interference, switching indicator, avoidance, Objectives
  40. [40] § 4. Experiments and Results Analysis › 4.3. Comparative Experiments ↔ experiment_v2/src/baselines.py, lines 150–249 · score 0.56 · post hoc, quality scores, hysteresis, reset, threshold, policy

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 · 1,629 lines · 74 KB · no license · 6 matches

The registry keeps no copy of this file: its repository has no license, so its authors keep all their rights to it. Your browser shows it from its source, with JavaScript.

It can be read at the source: paper_aligned_results_and_audit/analysis/scripts/summarize_revision_results.py.

Overview

Authors: Yuxuan Pan1, Ying Yan1,2, Dingyi Sun3, Zhenyu Li4, Zhixuan Zhang5, Jun Cai2, Dapeng Chen2, Qi Wu6, Zongyuan Shen7
ORCID iDs: Yuxuan Pan, Ying Yan, Dingyi Sun, Zhixuan Zhang, Jun Cai
  1. Reading Academy, Nanjing University of Information Science and Technology, Nanjing 210044, China
  2. School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China; (J.C.); (D.C.)
  3. School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China
  4. Nanjing Research Institute of Electronics Technology, Nanjing 210039, China
  5. School of Electronics & Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
  6. Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China
  7. College of Information Science and Technology, Jinan University, Guangzhou 510632, China
Institutions: Nanjing University of Information Science and Technology (China); Shanghai Jiao Tong University (China); Jinan University (China)
Journal: Sensors (Basel, Switzerland), volume 26, issue 17, article 5501
Dates: received 8 July 2026; accepted 28 August 2026; published online 30 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/s26175501 · PMID 42740121 · PMCID PMC13568378 · OpenAlex W7204802221
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: cellular / molecular (subfield)
Methods: Statistics, Machine learning
Keywords: HNP-DQN, cognitive radar, adaptive spectrum selection, deep reinforcement learning, polynomial feature expansion, channel switching cost
Topic: Wireless Signal Modulation Classification (Artificial Intelligence, Computer Science), according to OpenAlex
Citations: not cited yet (Europe PMC); 39 references in the paper

Abstract

Switching-aware spectrum selection requires balancing interference avoidance against retuning costs. This paper evaluates a hybrid neural–polynomial deep Q-network (HNP-DQN) in an eight-channel, measurement-driven 5 GHz testbed with exogenous sweeping and random interference. The architecture combines learned latent features with an element-wise second-order expansion, layer normalization (LayerNorm), and a dueling Double Deep Q-Network (DDQN) backbone. Files are separated before window construction, and the evaluation includes a pre-inspected pilot and two outcome-uninspected distance and power transfers. The comparison includes strong deterministic rules and a capacity-matched multilayer perceptron (MLP) trained with the same DDQN procedure. All methods are evaluated on common trajectories with paired inference across 10 independently trained seeds and Holm correction. Under deterministic sweeping, the schedule-aware rule was given the declared initial phase and one-channel-per-step direction and used an internal step counter to track the deterministic progression. These schedule variables and the corresponding step index are absent from HNP-DQN’s 48-dimensional observation. The rule matched the trajectory-wise dynamic-programming upper bound and outperformed HNP-DQN in all three settings (differences calculated as HNP-DQN minus the rule: −1.91, −3.51, and −1.97; all adjusted p=0.023). This information-asymmetric operational comparison shows the advantage attainable when the declared sweep specification and its progression are directly exploited; however, it does not provide a matched-information architectural ranking. By contrast, under random jamming, all comparisons between HNP-DQN and the threshold rule were inconclusive after correction, as were all six capacity-matched comparisons between HNP-DQN and the MLP. Of the 24 exploratory ablation comparisons, one favored the γ=0 variant in the random pilot, whereas the other 23 were inconclusive. Accordingly, this paper provides an information-aware, approximately parameter-matched reference for evaluating when explicit knowledge, observation-based control, or additional learning complexity is justified within the declared measurement-replay scope.

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 40 matches between paragraphs and lines of code.

TheRyans520/HNPDQN

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 6b62ded98eda36646f4174bc2cb3bc671e1bf75d, 5 September 2026
Languages: Python (65), Shell (1)
Size: 4,913 files, 66 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README, environment (requirements.txt, experiment_v2/requirements.txt), tests, continuous integration
Not found: license file, CITATION.cff, documentation
Tools: NumPy (41 files), PyTorch (19 files), pandas (18 files), Matplotlib (10 files), SciPy (4 files), seaborn (2 files), Pillow (1 file), TensorFlow (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
67 files, not copied: shown from their source

OSCR keeps no copy of these files: this repository has no license that allows it. The reader above shows each one from its source, fetched by your browser at commit 6b62ded, when its fingerprint is the one OSCR verified. How this works.

At the source: github.com/TheRyans520/HNPDQN

The paper's code and data availability statement is in the Data section.

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;
  • 66 scripts, each with its path and the digest of its content;
  • 40 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 Statement

The source code developed for this paper is publicly available at https://github.com/TheRyans520/HNPDQN (accessed on 27 August 2026). The RF Jamming dataset used in this paper is publicly available and documented by Ali et al. in “RF Jamming Dataset: A Wireless Spectral Scan Approach for Malicious Interference Detection”.

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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 9 authors, 6 keywords, 31 references.

Cite

This paper

Pan, Y., Yan, Y., Sun, D., Li, Z., Zhang, Z., Cai, J., Chen, D., Wu, Q., & Shen, Z. (2026). Evaluation of a Hybrid Neural-Polynomial Deep Q-Network for Switching-Aware Spectrum Selection in a Controlled Radio-Frequency Measurement-Replay Testbed. Sensors (Basel, Switzerland), 26(17), 5501. https://doi.org/10.3390/s26175501

BibTeX

@article{pan2026evaluation,
author = {Pan, Yuxuan and Yan, Ying and Sun, Dingyi and Li, Zhenyu and Zhang, Zhixuan and Cai, Jun and Chen, Dapeng and Wu, Qi and Shen, Zongyuan},
title = {{Evaluation of a Hybrid Neural-Polynomial Deep Q-Network for Switching-Aware Spectrum Selection in a Controlled Radio-Frequency Measurement-Replay Testbed}},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = aug,
volume = {26},
number = {17},
pages = {5501},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {1424-8220},
doi = {10.3390/s26175501},
url = {https://doi.org/10.3390/s26175501},
pmid = {42740121},
pmcid = {PMC13568378}
}

RIS

TY - JOUR
AU - Pan, Yuxuan
AU - Yan, Ying
AU - Sun, Dingyi
AU - Li, Zhenyu
AU - Zhang, Zhixuan
AU - Cai, Jun
AU - Chen, Dapeng
AU - Wu, Qi
AU - Shen, Zongyuan
TI - Evaluation of a Hybrid Neural-Polynomial Deep Q-Network for Switching-Aware Spectrum Selection in a Controlled Radio-Frequency Measurement-Replay Testbed
T2 - Sensors (Basel, Switzerland)
J2 - Sensors (Basel)
PY - 2026
DA - 2026/08/30
VL - 26
IS - 17
SP - 5501
SN - 1424-8220
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/s26175501
UR - https://doi.org/10.3390/s26175501
LA - en
ER -

CSL-JSON

{
"id": "10.3390/s26175501",
"type": "article-journal",
"title": "Evaluation of a Hybrid Neural-Polynomial Deep Q-Network for Switching-Aware Spectrum Selection in a Controlled Radio-Frequency Measurement-Replay Testbed",
"container-title": "Sensors (Basel, Switzerland)",
"author": [
{
"family": "Pan",
"given": "Yuxuan"
},
{
"family": "Yan",
"given": "Ying"
},
{
"family": "Sun",
"given": "Dingyi"
},
{
"family": "Li",
"given": "Zhenyu"
},
{
"family": "Zhang",
"given": "Zhixuan"
},
{
"family": "Cai",
"given": "Jun"
},
{
"family": "Chen",
"given": "Dapeng"
},
{
"family": "Wu",
"given": "Qi"
},
{
"family": "Shen",
"given": "Zongyuan"
}
],
"container-title-short": "Sensors (Basel)",
"volume": "26",
"issue": "17",
"page": "5501",
"DOI": "10.3390/s26175501",
"PMID": "42740121",
"PMCID": "PMC13568378",
"ISSN": "1424-8220",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/s26175501",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
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:10.3390/s26113488
Towards Interpretable Seizure Detection: An Excitation/Inhibition Dynamic Polynomial Network Framework for Electroencephalography.
Journal: Sensors (Basel, Switzerland)
In common: 2 authors
[2] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: TensorFlow, Pillow, PyTorch, 5 other tools, cellular / molecular
[3] doi:10.7554/elife.110588 [code]
Opening the black box toward a modular approach to spike sorting.
Journal: eLife
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[4] doi:10.1038/s41592-026-03194-8 [code]
Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering.
Journal: Nature methods
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[5] doi:10.1371/journal.pcbi.1014571 [code]
SynAPSeg: A novel dataset and image analysis framework for deep learning-based synapse detection and quantification.
Journal: PLoS computational biology
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[6] doi:10.1364/boe.605322 [code]
Generalized plaque digitization framework for multi-dimensional mesoscopic images.
Journal: Biomedical optics express
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[7] doi:10.1523/eneuro.0023-26.2026 [code]
Real-Time Segmentation and Classification of Birdsong Syllables for Learning Experiments.
Journal: eNeuro
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[8] doi:10.1038/s41467-026-74358-5 [code]
Brain-inspired spatial intelligence for embodied agents.
Journal: Nature communications
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[9] doi:10.1364/boe.600665 [code]
NeuroSeg-MF: robust neuron segmentation in two-photon Ca<sup>2+</sup> imaging using multi-feature fusion and detection-guided SAM.
Journal: Biomedical optics express
In common: TensorFlow, Pillow, PyTorch, 5 other tools
[10] doi:10.21203/rs.3.rs-9676637/v1 [code]
A Comprehensive Benchmarking of Spatial Deconvolution and Domain Detection Methods across Diverse Tissues and Spatial Transcriptomic Technologies
Journal: Research Square (preprint)
In common: TensorFlow, Pillow, PyTorch, 5 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.