Paper contribution

Evidence-Linked Point Load Test Measurement Uncertainty via Human-Supervised AI

Dragan Dimitrievski; Ljupco Dimitrievski; Teodor Dimitrievski; Marija Jovancevska

Proceedings
EUROCK 2026
Pages
1395-1400
Submitted
15 May 2026
Accepted
15 June 2026
Published
12 August 2026

Summary

Abstract

In rock engineering the point load strength index Is(50) informs rock strength classification, correlation-based estimation of uniaxial compressive strength (UCS), and rock-mass classification systems used in design. The reliability of each such decision depends on the evidence behind the laboratory value. Yet under ISO/IEC 17025:2017 accreditation, the measurement uncertainty of Is(50) and its supporting evidence are frequently fragmented across spreadsheets, certificates and folders, and rarely traceable as a single record. An uncertainty that is unquantified or undocumented does not disappear; it propagates into classification and design as unmanaged risk. This paper presents a pilot study of the documentation quality of Is(50) inputs. Using real records from an accredited laboratory that took part in an interlaboratory comparison, it reconstructs the Is(50) uncertainty budget from its physical sources, following JCGM 100:2008 and ISO/IEC 17025:2017 Clause 7.6. It then proposes an Evidence Traceability Matrix (ETM) linking each source to its required documentary evidence and clause, and a Documentation Completeness Score (DCS), a weighted clause-anchored indicator of record completeness, supported by a seven-stage human-supervised workflow in which AI produces the provisional candidate drafts requiring engineer approval. For the case dataset, repeatability driven by specimen heterogeneity dominates, and the expanded uncertainty is of the order of ±1.2 MPa (k=2) on a ~5 MPa index — a magnitude relevant to the strength-class boundaries the index informs. The contribution is a structured demonstration on real data and a purpose-built AI-assisted workflow for evidence-linked uncertainty documentation in accredited geotechnical laboratories, with preliminary scoring weights requiring multi-laboratory validation as the next step.

Contributors

Authors

  1. Dragan Dimitrievski Geing DOO, Skopje, North Macedonia, Republic of ORCID 0000-0002-3487-3382
  2. Ljupco Dimitrievski Ss. Cyril and Methodius University in Skopje, Faculty of Civil Engineering, Skopje, North Macedonia
  3. Teodor Dimitrievski Geing DOO, Skopje, North Macedonia, Republic of
  4. Marija Jovancevska Geing DOO, Skopje, North Macedonia, Republic of

Index terms

Keywords

Full text

Attachments

Works cited

References

  1. Amershi S, Begel A, Bird C et al. (2019) Software engineering for machine learning: a case study. Proc. 41st IEEE/ACM Int. Conf. on Software Engineering: Software Engineering in Practice (ICSE-SEIP), Montreal: 291–300. DOI: 10.1109/ICSE-SEIP.2019.00042
  2. ASTM D5731-16 (withdrawn 2025) Standard Test Method for Determination of the Point Load Strength Index of Rock and Application to Rock Strength Classifications. ASTM International, West Conshohocken, PA.
  3. Bieniawski ZT (1989) Engineering Rock Mass Classifications. John Wiley & Sons, New York.
  4. ISO 13528:2022 Statistical methods for use in proficiency testing by interlaboratory comparison. International Organization for Standardization, Geneva.
  5. ISO/IEC 17025:2017 General requirements for the competence of testing and calibration laboratories. International Organization for Standardization, Geneva.
  6. ISRM (1985) Suggested Method for Determining Point Load Strength. International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstracts 22(2): 51–60.
  7. JCGM 100:2008 Evaluation of measurement data — Guide to the expression of uncertainty in measurement (GUM). Joint Committee for Guides in Metrology, BIPM, Sèvres.
  8. Mosqueira-Rey E, Hernández-Pereira E, Alonso-Ríos D, Bobes-Bascarán J, Fernández-Leal Á (2023) Human-in-the-loop machine learning: a state of the art. Artificial Intelligence Review 56(4):3005–3054. DOI: 10.1007/s10462-022-10246-w
  9. Zai K, Mukti AP, Notty GS, Niswah SU, Refliandi, Oktivendra F (2025) Artificial intelligence in the non-clinical laboratory: enhancing good laboratory and documentation practices. International Journal of Pharmaceutics 685:126266. DOI: 10.1016/j.ijpharm.2025.126266
  10. Zhang W, Zhang R, Wu C et al. (2020) State-of-the-art review of soft computing applications in underground excavations. Geoscience Frontiers 11(4): 1095–1106. DOI: 10.1016/j.gsf.2019.12.003
  11. Zhao G-F, Wu Y (2025) Artificial intelligence in rock mechanics. International Journal of Rock Mechanics and Mining Sciences 195:106245. DOI: 10.1016/j.ijrmms.2025.106245