> For the complete documentation index, see [llms.txt](https://osintelligence-llc.gitbook.io/osintelligence/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://osintelligence-llc.gitbook.io/osintelligence/part-iv-the-evidence-what-worked/13-sovereign-ioc-classifier/references-and-provenance.md). # References & provenance ### References **PEFT + tooling:** Hu, E. J., et al. (2021). "LoRA: Low-Rank Adaptation of Large Language Models." [arXiv:2106.09685](https://arxiv.org/abs/2106.09685) · Dettmers, T., et al. (2023). "QLoRA: Efficient Finetuning of Quantized LLMs." *NeurIPS 2023*; [arXiv:2305.14314](https://arxiv.org/abs/2305.14314) · Zhou, C., et al. (2023). "LIMA: Less Is More for Alignment." [arXiv:2305.11206](https://arxiv.org/abs/2305.11206) · Wolf, T., et al. (2020). "Transformers." [arXiv:1910.03771](https://arxiv.org/abs/1910.03771) · Lhoest, Q., et al. (2021). "Datasets." [arXiv:2109.02846](https://arxiv.org/abs/2109.02846) · Unsloth AI (2024–2026). FastModel · Loshchilov, I., & Hutter, F. (2017). AdamW ([arXiv:1711.05101](https://arxiv.org/abs/1711.05101)) + SGDR cosine schedule ([arXiv:1608.03983](https://arxiv.org/abs/1608.03983)). **SLMs:** Abdin, M., et al. (2024). "Phi-3 Technical Report." [arXiv:2404.14219](https://arxiv.org/abs/2404.14219) · Jiang, A. Q., et al. (2023). "Mistral 7B." [arXiv:2310.06825](https://arxiv.org/abs/2310.06825) · Gemma Team (2024). [arXiv:2403.08295](https://arxiv.org/abs/2403.08295) · Touvron, H., et al. (2023). "Llama 2." [arXiv:2307.09288](https://arxiv.org/abs/2307.09288) · Alibaba Qwen Team (2025). Qwen 3.5 technical-report family. **Constrained decoding:** Willard, B. T., & Louf, R. (2023). [arXiv:2307.09702](https://arxiv.org/abs/2307.09702) · Beurer-Kellner, L., Fischer, M., & Vechev, M. (2024). "Guiding LLMs The Right Way." *ICML 2024*; [arXiv:2403.06988](https://arxiv.org/abs/2403.06988) · Geng, X., et al. (2025). "JSONSchemaBench." [arXiv:2501.10868](https://arxiv.org/abs/2501.10868) · Dong, Y., et al. (2024). "XGrammar." [arXiv:2411.15100](https://arxiv.org/abs/2411.15100) · guidance-ai (2025). llguidance · llama.cpp GBNF + JSON-schema grammars, and the server's router-mode + adapter hot-load documentation. **Format-tax (disconfirming lane):** Schall, M., & de Melo, G. (2025). "The Hidden Cost of Structure: How Constrained Decoding Affects Language Model Performance." *RANLP 2025*, 1074–1084 · Lee, I. Y., D’Antoni, L., & Berg-Kirkpatrick, T. (2026). "The Format Tax." [arXiv:2604.03616](https://arxiv.org/abs/2604.03616) · Shin, S., et al. (2025). "Lost in Space: Optimizing Tokens for Grammar-Constrained Decoding." [arXiv:2502.14969](https://arxiv.org/abs/2502.14969). **Instruction tuning + alignment:** Wei, J., et al. (2022). FLAN. *ICLR 2022*; [arXiv:2109.01652](https://arxiv.org/abs/2109.01652) · Ouyang, L., et al. (2022). InstructGPT. [arXiv:2203.02155](https://arxiv.org/abs/2203.02155) · Bai, Y., et al. (2022). "Constitutional AI." [arXiv:2212.08073](https://arxiv.org/abs/2212.08073). **CTI + NER (light anchoring):** Devlin, J., et al. (2019). "BERT." *NAACL 2019* · Strom, B. E., et al. (2018). *MITRE ATT\&CK: Design and Philosophy.* MITRE · OASIS Open (2021). *STIX 2.1.* **Method norms:** Munafò, M. R., et al. (2017). "A manifesto for reproducible science." [*Nat. Hum. Behav.* 1:0021](https://doi.org/10.1038/s41562-016-0021) · Nosek, B. A., et al. (2018). "The preregistration revolution." *PNAS* 115(11) · Wilson, E. B. (1927). *JASA* 22(158):209–212 · ODNI (2015). *ICD-203: Analytic Standards.* **Self-distillation context:** Zhang, R., et al. (2026). "Embarrassingly Simple Self-Distillation Improves Code Generation" (Apple SSD). [arXiv:2604.01193](https://arxiv.org/abs/2604.01193) · Kim, J., et al. (2026). "Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?" [arXiv:2603.24472](https://arxiv.org/abs/2603.24472). **In-series companions:** [*Sixteen Practices*](/osintelligence/part-ii-the-discipline/5-sixteen-practices.md) (Chapter 5; the Pair, the moat, the evidence ladder) · [*Corpus-Sovereign Self-Distillation*](/osintelligence/part-iv-the-evidence-what-worked/18-corpus-sovereign-self-distillation.md) (Chapter 18; the 9B calibration-retention sibling) · [*Sovereign CTI-NER*](/osintelligence/part-iv-the-evidence-what-worked/14-sovereign-cti-ner.md) (Chapter 14; the successor specialist) · [*The Sovereign Triad*](/osintelligence/part-i-the-architecture/1-the-sovereign-triad.md) (Chapter 1; the Pair's first half at architecture register) · [*Sovereign Optimization Flywheel*](/osintelligence/part-ii-the-discipline/8-sovereign-optimization-flywheel.md) (Chapter 8; this paper is L₄'s first cycle datum) · [*Sovereign Sustainability*](/osintelligence/part-v-the-frontier/22-sovereign-sustainability.md) (Chapter 22; the 219-hour envelope) · the sealed P4 spec/recipe/results chain (in the source repository). **Evidence & seal.** The capability probe behind this chapter, its final report reproduced verbatim with the training manifest, the 100%-vs-22% A/B, and the live-fire check, is in the record's evidence section: [IOC Classifier Micro-Agent (P4)](/osintelligence/evidence-and-seals/ioc-classifier-micro-agent-p4.md). (Report-class capability probe, Admiralty B2: it pre-dates the canonical-prefix sealing discipline, so it carries a validated report rather than a self-hash, and states its own small-N scope, as noted on the page.) ### AI-assistance disclosure Large language models were used as research tools in the preparation of this chapter: Claude Opus 4.6 (capability-probe seal, 2026-04-11); Claude Opus 4.7 (peer-review promotion, 2026-05-12). The model versions and roles named above keep the provenance of this chapter auditable. No AI system is listed as an author or credited as a contributor, in line with COPE and ICMJE guidance: an AI system cannot take responsibility for the work, cannot assert competing interests, and cannot enter a licence agreement. The author verified every claim in this chapter against the sealed artifacts and is solely accountable for it. **Citation (preferred):** Kistner, J. (2026). *Sovereign IOC Classifier: A Capability-Probe Demonstration of the First In-Weights Micro-Agent on Consumer-Hardware LoRA Substrate.* OSINTelligence LLC research whitepaper, version 2.1.0 (capability-probe seal, Admiralty B2; July 2026 System Update appended). Cited in-series by title. **License:** CC BY 4.0 (text). Code and data artifacts MIT per repository license. **Corresponding author:** Jamey Kistner, , OSINTelligence LLC (Columbus, OH). *** *The Sovereign Stack · Sovereign IOC Classifier · Chapter 13 · Part IV · v2.1.0 · License CC BY 4.0 · © Jamey Kistner, OSINTelligence LLC*