pith. machine review for the scientific record. sign in

arxiv: 2605.04257 · v1 · submitted 2026-05-05 · 💻 cs.LG

Recognition: 2 theorem links

HUGO-CS: A Hybrid-Labeled, Uncertainty-Aware, General-Purpose, Observational Dataset for Cold Spray

Stephen Price , Kyle Miller , Marco Musto , Kenneth Kroenlein , James Saal , Kyle Tsaknopoulos , Elke A. Rundensteiner , Danielle L. Cote
Authors on Pith no claims yet

Pith reviewed 2026-05-08 18:39 UTC · model grok-4.3

classification 💻 cs.LG
keywords cold sprayliterature extractionhybrid labelingobservational datasetLLM-assisted miningprocess optimizationuncertainty-aware labelingmanufacturing data
0
0 comments X

The pith

A hybrid human-AI extraction framework assembles 4,383 cold-spray experiments from 1,124 literature sources into one structured dataset.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents HUGO-CS, a large observational dataset of cold-spray experiments extracted from scientific literature to overcome the scarcity of machine-readable data for process optimization. Cold spraying involves many interdependent parameters, yet prior collections held only 137 samples, limiting modeling efforts. The authors built the HUGO framework to combine automated LLM labeling with selective manual refinement through Hierarchical Risk Mitigation, which flags high-risk records for review while keeping low-risk ones auto-labeled. Post-processing normalizes units, structures compositions, and consolidates descriptors, yielding 1,765 fully hand-labeled points as a quality benchmark. This scale-up supplies the volume needed for data-driven approaches in repair and manufacturing applications.

Core claim

The central claim is that a hybrid-labeled, uncertainty-aware extraction framework can reliably scale literature mining to produce HUGO-CS, a dataset of 4,383 cold-spray experiments with 144 features drawn from 1,124 sources, which exceeds the prior largest collection by a factor of thirty while releasing both the data and replication code under open license.

What carries the argument

The HUGO framework, which routes LLM-generated labels through Hierarchical Risk Mitigation to trigger manual review only for high-uncertainty cases, followed by unit normalization and chemistry structuring.

If this is right

  • Machine-learning models for cold-spray parameter optimization can now train on thirty times more experimental observations than before.
  • The 1,765 hand-labeled subset serves as a direct benchmark for testing automated extraction quality and higher-fidelity analyses.
  • Normalized continuous compositions and unit-standardized features enable direct comparison across sources that previously reported incompatible formats.
  • Process optimization studies gain access to a general-purpose observational resource spanning many feedstock chemistries and operating conditions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same risk-mitigation routing could be tested on extraction tasks in other materials or manufacturing domains where tables and figures dominate reporting.
  • If models trained on the full dataset outperform those trained only on hand-labeled data, it would indicate that the auto-labeled volume adds net signal despite residual noise.
  • Release of the complete dataset under CC-BY license allows community extensions such as adding new sources or linking to simulation outputs.
  • Scaling this approach might reduce the per-document extraction time below the reported 91 minutes once the framework is applied repeatedly.

Load-bearing premise

The hybrid process with risk-based manual review produces labels accurate enough for the auto-labeled majority to be useful alongside the hand-labeled benchmark.

What would settle it

A side-by-side error audit on a random sample of auto-labeled records versus independent manual re-extraction would show whether disagreement rates exceed acceptable thresholds for downstream modeling tasks.

Figures

Figures reproduced from arXiv: 2605.04257 by Danielle L. Cote, Elke A. Rundensteiner, James Saal, Kenneth Kroenlein, Kyle Miller, Kyle Tsaknopoulos, Marco Musto, Stephen Price.

Figure 1
Figure 1. Figure 1: Overview of the HUGO pipeline for cold-spray dataset construction. Articles are converted to view at source ↗
Figure 2
Figure 2. Figure 2: Visualization of composition processing in the HUGO framework. For each experiment, the primary, view at source ↗
Figure 3
Figure 3. Figure 3: (A) Visualization of extracted values per mechanical property, where blue indicates LLM-extracted view at source ↗
Figure 4
Figure 4. Figure 4: (A) Visualization of extracted values per mechanical property, where red indicates experiments view at source ↗
Figure 5
Figure 5. Figure 5: (a) Number of cold spray articles and extracted experiments published per year in HUGO-CS, and view at source ↗
Figure 6
Figure 6. Figure 6: (A) Visualization of the distribution of cold-spray systems reported across HUGO-CS, and (B) view at source ↗
Figure 7
Figure 7. Figure 7: (A) Visualization of leave-one-article-out (LOAO) yield strength predictions for experiments with view at source ↗
Figure 8
Figure 8. Figure 8: (A) Visualization of predicted versus actual microhardness values for the multi-class hardness model, view at source ↗
read the original abstract

Cold spraying is an increasingly common approach for repairing and manufacturing components due to its solid-state manufacturing capabilities. However, process optimization remains difficult due to many interdependent parameters and the lack of large-scale, machine-readable data to support modeling. While the scientific literature contains many relevant experiments, results are inconsistently reported (often in tables and figures) and use non-uniform units, limiting utilization at scale. To address these limitations, this work presents HUGO-CS, a literature-derived dataset of 4,383 cold-spray experiments with 144 features from 1,124 sources, exceeding the previous largest dataset (137 samples) by 30x. With completely manual extraction requiring an average of 91 minutes per document, this work designs and leverages a Hybrid-labeled, Uncertainty-aware, General-purpose, Observational extraction framework, called HUGO, to support this extraction. HUGO combines automated LLM-based labeling with targeted manual label refinement to handle this experimental result extraction process from scientific literature. To balance labeling efficiency with extraction accuracy, HUGO introduces a Hierarchical Risk Mitigation (HRM) to route LLM outputs with a high risk of potential errors for manual review, while retaining low-risk records as auto-labeled. Lastly, HUGO post-processing consolidates categorical descriptors, maps reported feedstock chemistries into structured continuous compositions, and normalizes units across sources. Of the 4,383 reported experiments, 1,765 are hand-labeled, providing a high-quality labeled subset for benchmarking, error analysis, and higher-fidelity data points. All code to replicate this work, along with the complete HUGO-CS dataset, are released under a CC-BY license at https://github.com/sprice134/HUGO.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript presents HUGO-CS, a literature-derived dataset of 4,383 cold-spray experiments with 144 features extracted from 1,124 sources. Extraction uses the HUGO framework, a hybrid approach combining LLM-based auto-labeling with Hierarchical Risk Mitigation (HRM) to route high-risk outputs for manual review, yielding 1,765 hand-labeled records. Post-processing normalizes units, maps feedstock chemistries to continuous compositions, and consolidates descriptors. The work claims this exceeds prior datasets by 30x and releases all code and data under CC-BY at the provided GitHub link.

Significance. If the hybrid extraction produces reliable labels, HUGO-CS would enable large-scale machine learning for cold-spray process optimization, addressing the field's data scarcity. The hybrid HRM strategy and post-processing pipeline offer a reusable template for observational dataset construction from scientific literature. Explicit release of code, data, and the hand-labeled benchmark subset supports reproducibility and downstream validation by others.

major comments (1)
  1. [Abstract and HUGO framework / HRM sections] Abstract and the HUGO framework description (including HRM routing): the central claim of a usable 4,383-experiment dataset (30x larger than prior work) depends on the reliability of the ~2,618 auto-labeled records. No quantitative metrics are reported for (a) the fraction of LLM outputs routed to manual review, (b) LLM-vs-human disagreement rates on reviewed cases, or (c) accuracy of retained auto-labels against the 1,765 hand-labeled benchmark on shared features. Post-processing steps cannot correct upstream extraction errors, so these statistics are required to substantiate the effective dataset size for modeling.
minor comments (2)
  1. [Abstract] The abstract references a prior largest dataset of 137 samples but does not cite the source; adding the reference would improve context for the 30x claim.
  2. [Results or dataset statistics section] Figure or table presenting the hand-labeled vs. auto-labeled split and any available error analysis would clarify the hybrid process outcomes.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their positive evaluation of the work's significance and for the constructive major comment on the HUGO framework. We address the concern point by point below and commit to revisions that will strengthen the manuscript's claims regarding dataset reliability.

read point-by-point responses

  1. Referee: [Abstract and HUGO framework / HRM sections] Abstract and the HUGO framework description (including HRM routing): the central claim of a usable 4,383-experiment dataset (30x larger than prior work) depends on the reliability of the ~2,618 auto-labeled records. No quantitative metrics are reported for (a) the fraction of LLM outputs routed to manual review, (b) LLM-vs-human disagreement rates on reviewed cases, or (c) accuracy of retained auto-labels against the 1,765 hand-labeled benchmark on shared features. Post-processing steps cannot correct upstream extraction errors, so these statistics are required to substantiate the effective dataset size for modeling.

    Authors: We agree that these quantitative metrics are essential to substantiate the reliability of the auto-labeled records and were not included in the original manuscript. The HRM component was intended to route only high-risk LLM outputs for manual review while retaining low-risk cases as auto-labeled, but explicit statistics on routing fraction, disagreement rates, and benchmark accuracy are needed for readers to assess the effective dataset quality. In the revised manuscript we will add a dedicated subsection (within the HUGO framework description) that reports these values computed from our extraction logs, including (a) the fraction of LLM outputs routed to manual review, (b) LLM-vs-human disagreement rates on the reviewed cases with breakdown by error type, and (c) accuracy of the retained auto-labels evaluated against the 1,765 hand-labeled records on overlapping features. This will be accompanied by a summary table and brief error analysis. We have retained all intermediate LLM outputs and review decisions, so these statistics can be generated directly without new experiments. The addition will clarify that post-processing addresses only unit and format inconsistencies while the HRM step targets extraction accuracy upstream. revision: yes

Circularity Check

0 steps flagged

No circularity: dataset extraction from external literature

full rationale

The paper constructs HUGO-CS by extracting and structuring experimental results from 1,124 published sources using a hybrid LLM-plus-manual process (HUGO with HRM). No equations, fitted parameters, predictions, or first-principles derivations appear. The central claims concern scale (4,383 experiments, 144 features) and the extraction workflow itself; these reduce to the external literature plus the described (non-self-referential) labeling rules, not to any internal loop or self-citation. The 1,765 hand-labeled subset is presented as an independent benchmark rather than a fitted input renamed as output. All load-bearing steps are externally grounded and falsifiable against the source papers.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central contribution is the curated dataset and extraction framework; no numerical free parameters are fitted because this is a data-collection effort rather than a modeling paper. The main assumption is that literature-reported experiments can be reliably extracted and standardized.

axioms (1)
  • domain assumption Scientific literature on cold spray contains extractable experimental results that can be standardized into a unified set of 144 features with consistent units and compositions.
    The entire dataset construction rests on the availability and parsability of reported data across 1,124 sources.
invented entities (1)
  • HUGO extraction framework no independent evidence
    purpose: Hybrid LLM-based labeling combined with targeted manual review via Hierarchical Risk Mitigation for literature data extraction
    New system introduced in this work to balance efficiency and accuracy; no independent external validation beyond the internal hand-labeled subset is provided.

pith-pipeline@v0.9.0 · 5651 in / 1469 out tokens · 106413 ms · 2026-05-08T18:39:19.513802+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

61 extracted references · 3 canonical work pages · 1 internal anchor

  1. [1]

    Springer (2021)

    Champagne Jr, V.K., Ozdemir, O.C., Nardi, A.: Practical cold spray. Springer (2021)

    2021

  2. [2]

    npj Materials Sustainability3(1), 36 (2025)

    Dowling, C., Tsaknopoulos, K., Ellingsen, M., Nardi, A., Cote, D.: Feasibility of on-site generated nitrogen as a sustainable cold spray process gas. npj Materials Sustainability3(1), 36 (2025)

    2025

  3. [3]

    Journal of Thermal Spray Technology34(1), 75–87 (2025)

    R´ ua Ram´ ırez, E., Silvello, A., Torres Diaz, E., Vaz, R.F., Garcia Cano, I.: Reusing 316l stainless steel feedstock powder for cold spray deposition. Journal of Thermal Spray Technology34(1), 75–87 (2025)

    2025

  4. [4]

    Journal of thermal spray technology30(1), 344–357 (2021)

    Ozdemir, O.C., Schwartz, P., Muftu, S., Thompson, F.C., Crawford, G.A., Nardi, A.T., Champagne Jr, V.K., Widener, C.A.: High rate deposition in cold spray. Journal of thermal spray technology30(1), 344–357 (2021)

    2021

  5. [5]

    International Materials Reviews61(7), 437–455 (2016)

    Champagne, V., Helfritch, D.: The unique abilities of cold spray deposition. International Materials Reviews61(7), 437–455 (2016)

    2016

  6. [6]

    Grubbs, J.: Exploring the impact of metallic powder quality on cold spray processing and consolidated material performance. Ph.D. thesis, Worcester Polytechnic Institute (2023)

    2023

  7. [7]

    Applied Surface Science451, 56–66 (2018)

    Huang, C., Yan, X., Li, W., Wang, W., Verdy, C., Planche, M., Liao, H., Montavon, G.: Post-spray modification of cold-sprayed ni-ti coatings by high-temperature vacuum annealing and friction stir processing. Applied Surface Science451, 56–66 (2018)

    2018

  8. [8]

    Materials Characterization206, 113,350 (2023)

    Wu, D., Xu, Y., Li, W., Fan, N., Yang, Y., Yin, S.: Significant improvement of mechanical proper- ties of cold-spray-additive manufactured feconicrmn high-entropy alloy via post-annealing. Materials Characterization206, 113,350 (2023)

    2023

  9. [9]

    Journal of Thermal Spray Technology30(6), 1493–1511 (2021)

    Sinclair-Adamson, R., Harbidge, M., Murray, R.: Sintering of cold spray additively manufactured alu- minum 6061. Journal of Thermal Spray Technology30(6), 1493–1511 (2021)

    2021

  10. [10]

    Journal of Thermal Spray Tech- nology33(2), 629–651 (2024)

    Eftekhari, N., Jahed, H.: Comparative analysis of microstructural and mechanical attributes in low- pressure cold-spray coatings: impact of varied cu feedstock powders. Journal of Thermal Spray Tech- nology33(2), 629–651 (2024)

    2024

  11. [11]

    Processes12(10), 2216 (2024)

    Wang, Y., Wong, B.C., Chan, T.M., Voyle, R.: Towards strength–ductility synergy in cold spray for manufacturing and repair application: A review. Processes12(10), 2216 (2024)

    2024

  12. [12]

    Materials Science and Engineering: A662, 72–79 (2016) 19

    Coddet, P., Verdy, C., Coddet, C., Debray, F.: On the mechanical and electrical properties of copper- silver and copper-silver-zirconium alloys deposits manufactured by cold spray. Materials Science and Engineering: A662, 72–79 (2016) 19

    2016

  13. [13]

    Surface and Coatings Technology254, 11–20 (2014)

    Luo, X.T., Li, C.X., Shang, F.L., Yang, G.J., Wang, Y.Y., Li, C.J.: High velocity impact induced microstructure evolution during deposition of cold spray coatings: A review. Surface and Coatings Technology254, 11–20 (2014)

    2014

  14. [14]

    Additive Manufacturing36, 101,371 (2020)

    Sample, C.M., Champagne, V.K., Nardi, A.T., Lados, D.A.: Factors governing static properties and fatigue, fatigue crack growth, and fracture mechanisms in cold spray alloys and coatings/repairs: A review. Additive Manufacturing36, 101,371 (2020)

    2020

  15. [15]

    Journal of Thermal Spray Technology34(1), 37–74 (2025)

    Sudigdo, P., Bhattiprolu, V.S., Hussain, T.: Cold spray of ni-based superalloys: A review on processing and residual stress. Journal of Thermal Spray Technology34(1), 37–74 (2025)

    2025

  16. [16]

    Materials Science and Engineering: A776, 139,024 (2020)

    Wei, Y.K., Luo, X.T., Chu, X., Huang, G.S., Li, C.J.: Solid-state additive manufacturing high perfor- mance aluminum alloy 6061 enabled by an in-situ micro-forging assisted cold spray. Materials Science and Engineering: A776, 139,024 (2020)

    2020

  17. [17]

    Journal of Materials Science & Technology170, 47–64 (2024)

    Yin, S., Fan, N., Huang, C., Xie, Y., Zhang, C., Lupoi, R., Li, W.: Towards high-strength cold spray additive manufactured metals: Methods, mechanisms, and properties. Journal of Materials Science & Technology170, 47–64 (2024)

    2024

  18. [18]

    Journal of thermal spray technology22(7), 1140–1153 (2013)

    Wong, W., Vo, P., Irissou, E., Ryabinin, A., Legoux, J.G., Yue, S.: Effect of particle morphology and size distribution on cold-sprayed pure titanium coatings. Journal of thermal spray technology22(7), 1140–1153 (2013)

    2013

  19. [19]

    Surface and Coatings Technology304, 592–605 (2016)

    Kumar, S., Bae, G., Lee, C.: Influence of substrate roughness on bonding mechanism in cold spray. Surface and Coatings Technology304, 592–605 (2016)

    2016

  20. [20]

    Materials & design29(2), 297–304 (2008)

    Li, W.Y., Zhang, C., Guo, X., Zhang, G., Liao, H., Li, C.J., Coddet, C.: Effect of standoff distance on coating deposition characteristics in cold spraying. Materials & design29(2), 297–304 (2008)

    2008

  21. [21]

    Beltagy, I., Lo, K., Cohan, A.: Scibert: A pretrained language model for scientific text. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp. 3615–3620 (2019)

    2019

  22. [22]

    In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp

    Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: Pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1192–1200 (2020)

    2020

  23. [23]

    In: International conference on theory and practice of digital libraries, pp

    Lopez, P.: Grobid: Combining automatic bibliographic data recognition and term extraction for schol- arship publications. In: International conference on theory and practice of digital libraries, pp. 473–474. Springer (2009)

    2009

  24. [24]

    International Journal on Document Analysis and Recognition (IJDAR)18(4), 317–335 (2015)

    Tkaczyk, D., Szostek, P., Fedoryszak, M., Dendek, P.J., Bolikowski, L.: Cermine: automatic extraction of structured metadata from scientific literature. International Journal on Document Analysis and Recognition (IJDAR)18(4), 317–335 (2015)

    2015

  25. [25]

    In: Ninth international conference on document analysis and recognition (ICDAR 2007), vol

    Smith, R.: An overview of the tesseract ocr engine. In: Ninth international conference on document analysis and recognition (ICDAR 2007), vol. 2, pp. 629–633. IEEE (2007)

    2007

  26. [26]

    Mehta, V.: Camelot: Pdf table extraction for humans.https://github.com/camelot-dev/camelot (2018)

    2018

  27. [27]

    In: 2017 ACM/IEEE joint conference on digital libraries (JCDL), pp

    Bast, H., Korzen, C.: A benchmark and evaluation for text extraction from pdf. In: 2017 ACM/IEEE joint conference on digital libraries (JCDL), pp. 1–10. IEEE (2017)

    2017

  28. [28]

    In: International Conference on Information, pp

    Meuschke, N., Jagdale, A., Spinde, T., Mitrovi´ c, J., Gipp, B.: A benchmark of pdf information ex- traction tools using a multi-task and multi-domain evaluation framework for academic documents. In: International Conference on Information, pp. 383–405. Springer (2023)

    2023

  29. [29]

    Journal of chemical information and modeling56(10), 1894–1904 (2016)

    Swain, M.C., Cole, J.M.: Chemdataextractor: a toolkit for automated extraction of chemical information from the scientific literature. Journal of chemical information and modeling56(10), 1894–1904 (2016)

    1904

  30. [30]

    Chemical Science13(39), 11,487–11,495 (2022)

    Huang, S., Cole, J.M.: Batterydataextractor: battery-aware text-mining software embedded with bert models. Chemical Science13(39), 11,487–11,495 (2022)

    2022

  31. [31]

    Nature Communications15(1), 1569 (2024)

    Polak, M.P., Morgan, D.: Extracting accurate materials data from research papers with conversational language models and prompt engineering. Nature Communications15(1), 1569 (2024)

    2024

  32. [32]

    Integrating Materials and Manufacturing Innovation pp

    Immanuel, J., Mahata, A.: Enhancing materials data workflows through object-oriented design and large language models. Integrating Materials and Manufacturing Innovation pp. 1–12 (2025)

    2025

  33. [33]

    Mineru: An open-source solution for precise document content extraction.arXiv preprint arXiv:2409.18839, 2024

    Wang, B., Xu, C., Zhao, X., Ouyang, L., Wu, F., Zhao, Z., Xu, R., Liu, K., Qu, Y., Shang, F., et al.: Mineru: An open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839 (2024)

    work page arXiv 2024

  34. [34]

    Ac- cessed 2026-01-01

    Crossref: Rest api.https://www.crossref.org/documentation/retrieve-metadata/rest-api/. Ac- cessed 2026-01-01

    2026

  35. [35]

    Champagne, V.K., Leyman, P., Helfritch, D.: Magnesium repair by cold spray. Tech. rep. (2008)

    2008

  36. [36]

    Additive manufacturing27, 595–605 (2019)

    Chen, C., Xie, Y., Yan, X., Yin, S., Fukanuma, H., Huang, R., Zhao, R., Wang, J., Ren, Z., Liu, M., et al.: Effect of hot isostatic pressing (hip) on microstructure and mechanical properties of ti6al4v alloy 20 fabricated by cold spray additive manufacturing. Additive manufacturing27, 595–605 (2019)

    2019

  37. [37]

    Journal of Thermal Spray Technology23(5), 765–785 (2014)

    Olakanmi, E., Doyoyo, M.: Laser-assisted cold-sprayed corrosion-and wear-resistant coatings: a review. Journal of Thermal Spray Technology23(5), 765–785 (2014)

    2014

  38. [38]

    Quantitative science studies1(1), 377–386 (2020)

    Baas, J., Schotten, M., Plume, A., Cˆ ot´ e, G., Karimi, R.: Scopus as a curated, high-quality bibliometric data source for academic research in quantitative science studies. Quantitative science studies1(1), 377–386 (2020)

    2020

  39. [39]

    Advances in neural information processing systems33, 1877–1901 (2020)

    Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Advances in neural information processing systems33, 1877–1901 (2020)

    1901

  40. [40]

    Hsieh, C.P., Sun, S., Kriman, S., Acharya, S., Rekesh, D., Jia, F., Zhang, Y., Ginsburg, B.: Ruler: What’s the real context size of your long-context language models? arXiv preprint arXiv:2404.06654 (2024)

    work page internal anchor Pith review arXiv 2024

  41. [41]

    Transactions of the association for computational linguistics 12, 157–173 (2024)

    Liu, N.F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., Liang, P.: Lost in the middle: How language models use long contexts. Transactions of the association for computational linguistics 12, 157–173 (2024)

    2024

  42. [42]

    In: Extended abstracts of the 2021 CHI conference on human factors in computing systems, pp

    Reynolds, L., McDonell, K.: Prompt programming for large language models: Beyond the few-shot paradigm. In: Extended abstracts of the 2021 CHI conference on human factors in computing systems, pp. 1–7 (2021)

    2021

  43. [43]

    OpenAI: Openai api (o4-mini model).https://platform.openai.com/docs/models(2025)

    2025

  44. [44]

    arXiv e-prints pp

    Geng, S., Cooper, H., Moskal, M., Jenkins, S., Berman, J., Ranchin, N., West, R., Horvitz, E., Nori, H.: Generating structured outputs from language models: Benchmark and studies. arXiv e-prints pp. arXiv–2501 (2025)

    2025

  45. [45]

    12–34 (2024)

    Tang, X., Zong, Y., Phang, J., Zhao, Y., Zhou, W., Cohan, A., Gerstein, M.: Struc-bench: Are large language models good at generating complex structured tabular data? In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pp. 12–34 (2024)

    2024

  46. [46]

    Naval research logistics quarterly 2(1-2), 83–97 (1955)

    Kuhn, H.W.: The hungarian method for the assignment problem. Naval research logistics quarterly 2(1-2), 83–97 (1955)

    1955

  47. [47]

    DOI 10.1520/E0008 E0008M-25

    ASTM International: Standard test methods for tension testing of metallic materials (2025). DOI 10.1520/E0008 E0008M-25. URLhttps://store.astm.org/e0008_e0008m-25.html. Accessed 2026- 01-30

    work page doi:10.1520/e0008 2025

  48. [48]

    Surface Engineering36(10), 1022–1031 (2020)

    Campbell, J.P., Astarita, A., Viscusi, A., Saha, G.C.: Investigation of strain-hardening characteristics of cold-sprayed al–al2o3 coatings: a combined nanoindentation and expanding cavity models approach. Surface Engineering36(10), 1022–1031 (2020)

    2020

  49. [49]

    JOM74(1), 249–259 (2022)

    Tsaknopoulos, K., Sousa, B., Massar, C., Grubbs, J., Siopis, M., Cote, D.: A through-process experi- mental approach to enable optimization of cold sprayed al 7075 consolidation performance. JOM74(1), 249–259 (2022)

    2022

  50. [50]

    Journal of Materials Research and Technology30, 1341–1353 (2024)

    Lama, A., Sarvesha, R., John, D., Paul, T., Sukumaran, A., Agarwal, A.: Role of nitrogen and helium gases on microstructure and anisotropic mechanical properties of cold-sprayed scalmalloy deposits. Journal of Materials Research and Technology30, 1341–1353 (2024)

    2024

  51. [51]

    Materials & Design 222, 111,105 (2022)

    Tsaknopoulos, K., Grubbs, J., Sousa, B.C., Siopis, M., Nardi, A., Cote, D.L.: Evaluation of a laser powder bed fusion designer al-mg-zr-si alloy for cold spray additive manufacturing. Materials & Design 222, 111,105 (2022)

    2022

  52. [52]

    Materials Performance and Characterization9(1), 324–345 (2020)

    Bhat, A., Neu, R.: On the constraint factor relating uniaxial and indentation yield strength of polycrys- talline materials using spherical microindentation. Materials Performance and Characterization9(1), 324–345 (2020)

    2020

  53. [53]

    Journal of Materials Research and Technology9(4), 9073–9079 (2020)

    Wang, W., Han, P., Wang, Y., Zhang, T., Peng, P., Qiao, K., Wang, Z., Liu, Z., Wang, K.: High- performance bulk pure al prepared through cold spray-friction stir processing composite additive man- ufacturing. Journal of Materials Research and Technology9(4), 9073–9079 (2020)

    2020

  54. [54]

    Surface and Coatings Technology 481, 130,644 (2024)

    Pandey, A., Gupta, A., Kumar, D., Goyal, R.: Hvof-sprayed surface coating with various compositions of co-nicraly-al2o3 to minimize sediment erosion in hydraulic turbines. Surface and Coatings Technology 481, 130,644 (2024)

    2024

  55. [55]

    Journal of Materials Research and Technology 34, 1549–1558 (2025)

    D´ ıaz, E.T., Silvello, A., Ramirez, E.R., Vaz, R.F., Cano, I.G.: Graphene nanoplatelets in titanium coatings deposited by cold spray: Mechanical properties. Journal of Materials Research and Technology 34, 1549–1558 (2025)

    2025

  56. [56]

    Mapan37(4), 859 (2022) 21

    Kumar, S., Pandey, S.M.: The study of assessment parameters and performance measurement of cold spray technique: A futuristic approach towards additive manufacturing. Mapan37(4), 859 (2022) 21

    2022

  57. [57]

    Materials Letters316, 132,090 (2022)

    Xie, Y., Fan, N., Yang, J., Li, W., Lupoi, R., Guo, X., Huang, R., Yin, S.: Improvement of tensile strength of cold sprayed fe deposits via in-process powder preheating. Materials Letters316, 132,090 (2022)

    2022

  58. [58]

    Materials11(5), 853 (2018)

    Bai, Y., Wang, Z., Li, X., Huang, G., Li, C., Li, Y.: Microstructure and mechanical properties of zn-ni-al2o3 composite coatings. Materials11(5), 853 (2018)

    2018

  59. [59]

    Transactions of the Indian Institute of Metals76(8), 2063–2072 (2023)

    Yao, Z., Xiao, G., Ma, K., Feng, L.: Microstructure and properties of alcrcofe x nicu high-entropy alloy coating synthesized via cold spraying-assisted induction remelting method. Transactions of the Indian Institute of Metals76(8), 2063–2072 (2023)

    2063

  60. [60]

    depth sensing indentation analysis

    Poza, P., M´ unez, C., Garrido-Maneiro, M., Vezz` u, S., Rech, S., Trentin, A.: Mechanical properties of inconel 625 cold-sprayed coatings after laser remelting. depth sensing indentation analysis. Surface and Coatings Technology243, 51–57 (2014)

    2014

  61. [61]

    Engineering Failure Analysis175, 109,581 (2025) 22

    Kundu, S., Stamoulis, K.: Qualitative evaluation of failure mechanisms of aluminium 6061-t6 cold spray repairs. Engineering Failure Analysis175, 109,581 (2025) 22

    2025