Celiums Research Labs

White Papers

Open research from Celiums Research Labs — a division of Celiums Solutions, LLC. Papers, preprints, and technical reports, released under open licenses. Read them, cite them, build on them.

● Published 2026 DOI: 10.5281/zenodo.20531347 GPL-3.0 · CC-BY-SA-4.0

Proprioceptive Channels: a Native Behavioral Control Axis for Language Models

Mario Gutierrez · Celiums Research Labs

We inject six external cognitive-state channels — memory, affect, time, ethics, identity, and continuity — into a frozen Gemma 4 E2B model through a small gated cross-attention adapter, and show the model learns to use them across all six capabilities. Under direct conflict, where the text prompt and the channel state disagree, the channel overrides the prompt 264 of 265 times: a measurable, perpendicular axis of behavioral control that is orthogonal to in-context instruction. We further reproduce the effect from scratch and report the honest negatives along the way.

proprioception conditioning Gemma interpretability
● Published · preprint 2026 DOI: 10.5281/zenodo.20436643 Apache-2.0 · CC-BY-4.0

Hyphae v2: Hash-Chained Verbatim Quotation — a Verifiable Provenance Layer for Grounded Retrieval

Mario Gutierrez · Celiums Research Labs

Hyphae is a cognitive substrate that answers grounded queries by verbatim quotation of hash-chained memory fragments — with no LLM in the cognition path, and a cryptographic audit relation between every output and its sources. Faithfulness is true by construction: every answer is a tamper-evident quote of a stored fragment, not a generated paraphrase. Version 2 implements this provenance layer and measures it against retrieval baselines.

verifiable provenance grounded retrieval hash chain machine memory

Our research is open. Each paper is released under the license shown on its card; that license — not our Terms — governs your rights to use, modify, and redistribute it. When you build on this work, please cite the corresponding paper or DOI. Questions: hello@celiums.ai.