
In January 2026 two papers were deposited on Zenodo establishing that information loss at dimensional boundaries in discrete systems is a geometric phenomenon with an architecture-independent magnitude: 86.01% ± 2.39% in cellular automata across 1,500 patterns (Thornhill 2026b, DOI 10.5281/zenodo.18262424, 01/14/2026), and 84.39% ± 1.55% on transformer hidden states (GPT-2, Gemma-2), supported by a formal proof of the component transformations S, R, and D (Thornhill 2026c, DOI 10.5281/zenodo.18319430, 01/20/2026). It was predicted, in the closing discussion of Thornhill 2026c, that the geometric account should hold across substrates wherever density dilution and neighborhood-structure expansion occur together at a representational boundary. In March 2026, Barman, Starenky, Bodnar, Narasimhan, and Gopinath independently published two arXiv preprints (arXiv:2603.27116 and arXiv:2604.06222) reporting that production retrieval embedding models — MiniLM-L6-v2, BGE-base, BGE-large — concentrate their variance into approximately 16 effective dimensions regardless of nominal dimensionality (384, 768, 1024), and that this concentration places those models in an interference-vulnerable geometric regime that reproduces quantitative signatures of human memory failure (power-law forgetting with exponent b = 0.460 ± 0.183, Deese–Roediger–McDermott false-alarm rate of 0.583, spacing-effect ordering, tip-of-tongue behavior). They establish a parallel theorem — the No-Escape Theorem — characterizing what cannot be repaired within semantically continuous kernel-threshold memory systems. The two bodies of work are methodologically distinct. They use different metrics (Φ = R·S + D vs. participation ratio), study different substrates (cellular automata and transformer hidden states vs. pretrained retrieval embeddings), and report different specific quantities (an 86% loss constant in Φ vs. a fixed point at ~16 effective dimensions across nominal sizes). They also reach the same broader conclusion from independent directions: that representational memory failure is a geometric property of the embedding operation, not a property of any particular architecture, training regime, or biological substrate. The present note records the chronology of the two lines of evidence in a single citable document, summarizes the methodological differences, and identifies the substantive convergence: an architecture-independent geometric fixed point as the principal explanatory mechanism for representational memory failure in the systems studied.
This is a synthesis note bridging two parallel lines of evidence on the geometric structure of representational memory failure. The author's prior work (Thornhill 2026b, DOI 10.5281/zenodo.18262424, deposited 01/14/2026; Thornhill 2026c, DOI 10.5281/zenodo.18319430, deposited 01/20/2026) established the dimensional-loss constant in cellular automata and transformer hidden states. Barman et al. (arXiv:2603.27116, arXiv:2604.06222, posted 03/28/2026 and 03/27/2026 respectively) report parallel findings on production retrieval embedding spaces using participation-ratio methodology. The present note positions both contributions on a single citable surface and identifies the substantive convergence at the level of architecture-independent geometric fixed points without claiming numerical equivalence between the specific quantities reported by the two methodologies.
dimensional embedding, architecture independence, semantic memory, geometric memory failure, dimensional loss theorem, embedding models, 86 percent scaling law, persistence, information loss, participation ratio, representational memory, substrate universality
dimensional embedding, architecture independence, semantic memory, geometric memory failure, dimensional loss theorem, embedding models, 86 percent scaling law, persistence, information loss, participation ratio, representational memory, substrate universality
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
