Metraipolis › archive › dc_130ffe288189
The Cross-Substrate Access Assay: What an Indicator Test Must Declare to Travel from Brain to Language Model — arXiv:2609.22300
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22300
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T23:40:20.988Z
- SHA-256 of the archived text
8af310d8a404b840419bf606b5e29ab6910519b9dd6bd9a1a8ac5f79492d9551- Stable URL of this page
https://metraipolis.com/documento/dc_130ffe288189
How to cite
The Cross-Substrate Access Assay: What an Indicator Test Must Declare to Travel from Brain to Language Model — arXiv:2609.22300 — arXiv (en), https://arxiv.org/abs/2609.22300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_130ffe288189 (Metraipolis archive dc_130ffe288189, sha256 8af310d8a404b840419bf606b5e29ab6910519b9dd6bd9a1a8ac5f79492d9551)
BibTeX
@misc{dc130ffe288189,
title = {The Cross-Substrate Access Assay: What an Indicator Test Must Declare to Travel from Brain to Language Model — arXiv:2609.22300},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22300},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_130ffe288189; sha256 8af310d8a404b840419bf606b5e29ab6910519b9dd6bd9a1a8ac5f79492d9551},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Testing an artificial system for a property linked to consciousness means applying a measurement developed on brains to a system that is not one. Such a transfer must re-examine five parts of the procedure: the competing statistical models, how they are fitted, the unit the inference generalizes over, the quantity the uncertainty interval is about, and the rule that turns a result into a verdict. The Cross-Substrate Access Assay declares all five. Because brain and model signals share no physical scale, every model is scored by the cross-entropy it assigns to held-out data, in nats per trial. The test case is the global neuronal workspace theory, which predicts that near threshold a stimulus either enters a capacity-limited workspace or does not, so that single-trial responses form a mixture of two states. A published test of this prediction on twenty people's electroencephalograms partly reproduces in a re-implementation: the first crossing and the broad ordering over time match, the window-by-window agreement does not. On 12,000 synthetic datasets generated with a single graded state, all of them members of the families the procedure fits and none within 0.0067 nat per trial of the decision boundary, the two models of that test carried over unchanged reported two states in 989 and the expanded families in none; on 600 datasets carrying a mixture the expanded procedure reported two states in 599. Its nominal 95% interval contained the procedure's mean result less often than the required 90% at six of twelve graded settings. No claim about experience is made. Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-22 in cond-mat.dis-nn). Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Neurons and Cognition (q-bio.NC). Pagina del lavoro: https://arxiv.org/abs/2609.22300 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T22:46:33.837Z dalla pagina https://arxiv.org/catchup/cond-mat.dis-nn/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).