Linking Repository Context and Laboratory Context

This evidence synthesis examines anchored retrieval in computational mineral physics workflows. It argues that the appropriate object of evaluation is the linked history of sample preparation, pressure-temperature path, instrument output, code version, fit, and scientific claim, not a model score in isolation. The review brings together the assigned studies with established work on uncertainty, robustness, provenance, and governance. Across these literatures, a common problem emerges: a plausible conclusion may depend on an unrecorded stress state, preprocessing choice, or alternative structural interpretation. The proposed framework separates evidence quality, model behavior, decision policy, and operational monitoring, then asks how each layer changes under distribution shift, adversarial pressure, or incomplete information. It recommends evaluation by slices and repeated trials, explicit reject and escalation policies, preservation of data and reasoning lineage, and prospective monitoring tied to defined actions. The result is a research agenda for systems that are efficient enough to use but also bounded enough to audit. No new experiment is claimed; the article develops a comparative conceptual model and identifies tests that would make future empirical claims more credible.

1. Ma, Mingjun, et al. "MuSK: Multi-Scale Knowledge Learning for Provenance-Graph Anomaly Detection." *Computer Networks* 289 (2026): 112728.
2. Li, Yuanhao, et al. "BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models." *arXiv preprint arXiv:2605.09134* (2026).
3. Chen, Huawei, et al. "Possible H2O Storage in the Crystal Structure of CaSiO3 Perovskite." *Physics of the Earth and Planetary Interiors* 299 (2020): 106412.
4. Hu, Yuntong, et al. "LARGER: Lexically Anchored Repository Graph Exploration and Retrieval." *arXiv preprint arXiv:2605.16352* (2026).
5. King, Samuel T., and Peter M. Chen. "Backtracking Intrusions." *Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles*, 2003, pp. 223-236.
6. Milajerdi, Sadegh M., et al. "HOLMES: Real-Time APT Detection through Correlation of Suspicious Information Flows." *2019 IEEE Symposium on Security and Privacy*, 2019, pp. 1137-1152.
7. Han, Xueyuan, et al. "UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats." *Network and Distributed System Security Symposium*, 2020.
8. Pasquier, Thomas, et al. "Runtime Analysis of Whole-System Provenance." *Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security*, 2017, pp. 1601-1614.
9. Schlichtkrull, Michael, et al. "Modeling Relational Data with Graph Convolutional Networks." *The Semantic Web*, Springer, 2018, pp. 593-607.
10. Hamilton, William L., Rex Ying, and Jure Leskovec. "Inductive Representation Learning on Large Graphs." *Advances in Neural Information Processing Systems*, vol. 30, 2017.
11. Velickovic, Petar, et al. "Graph Attention Networks." *International Conference on Learning Representations*, 2018.
12. Chandola, Varun, Arindam Banerjee, and Vipin Kumar. "Anomaly Detection: A Survey." *ACM Computing Surveys*, vol. 41, no. 3, 2009, article 15.
13. Sommer, Robin, and Vern Paxson. "Outside the Closed World: On Using Machine Learning for Network Intrusion Detection." *2010 IEEE Symposium on Security and Privacy*, 2010, pp. 305-316.
14. Liao, Xiaojing, et al. "Acing the IOC Game: Toward Automatic Discovery and Analysis of Open-Source Cyber Threat Intelligence." *Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security*, 2016, pp. 755-766.