A survey of published research, from the Essentia Memoria newsroom. It lists real papers, each looked up at its DOI registry; the game has not repeated their results.

Research survey

What AI research has found: reading burnt and rolled scrolls

Happened: October 28, 2026 at 11:02 PM UTC · Published: October 28, 2026 at 11:02 PM UTC

11 published works on reading burnt and rolled scrolls, each looked up at its DOI registry before it was listed here, with what each one reports in plain words.

Watch

Explanatory visualisation, drawn from the record's numbers. It is not footage of the event: nobody filmed it.

Listen

Transcript

News from the Essentia Memoria game universe. What AI research has found: reading burnt and rolled scrolls. 11 published works on reading burnt and rolled scrolls, each looked up at its DOI registry before it was listed here, with what each one reports in plain words. This survey lists what each paper reports. The game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited. This report was written from the world record by a fixed template. The full story and its source records are on essentiamemoria.com.

The question

How do computers read scrolls that can no longer be opened, such as the papyri buried by Vesuvius?

Claims, and where each one comes from

Where this research lives in the game (a place the world grammar builds)archive → library
Game simulation · Set in code src/lib/world-grammar/place-grammar.ts · resolvePurpose('archive')
Published works in this survey, each resolved at its DOI registry11
Real-world knowledge · Source [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11]
X-ray scans and software that unrolls the scroll on screen read a charred scroll from En-Gedi without opening it.Seales 2016
Real-world knowledge · Source [1]
Carbon ink on the Herculaneum papyri leaves a faint trace in X-ray scans, and a trained model can make it visible.Parker 2019
Real-world knowledge · Source [2]
Generating Grid Multi-Scroll Attractors in Memristive Neural NetworksLai 2022
Real-world knowledge · Source [3]
Generation ofn-double scrolls via cellular neural networksArena 1996
Real-world knowledge · Source [4]
Privacy Protection of Medical Data Based on Multi-Scroll Memristive Hopfield Neural NetworkYu 2022
Real-world knowledge · Source [5]
Initial offset boosting coexisting attractors in memristive multi-double-scroll Hopfield neural networkZhang 2020
Real-world knowledge · Source [6]
Dynamics analysis and hardware implementation of multi-scroll hyperchaotic hidden attractors based on locally active memristive Hopfield neural networkTang 2023
Real-world knowledge · Source [7]
Symmetric multi-scroll attractors in magnetized Hopfield neural network under pulse controlled memristor and pulse current stimulationWan 2023
Real-world knowledge · Source [8]
Multidirectional Multidouble-Scroll Hopfield Neural Network With Application to Image EncryptionZhang 2024
Real-world knowledge · Source [9]
Symmetric multi-double-scroll attractors in Hopfield neural network under pulse controlled memristorLi 2024
Real-world knowledge · Source [10]
Generating n-Scroll Chaotic Attractors From a Memristor-Based Magnetized Hopfield Neural NetworkLin 2022
Real-world knowledge · Source [11]

References, checked at their registry

[1] Seales (2016). From damage to discovery via virtual unwrapping: Reading the scroll from En-Gedi. Science Advances. doi:10.1126/sciadv.1601247
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “From damage to discovery via virtual unwrapping: Reading the scroll from En-Gedi” (2016)
[2] Parker (2019). From invisibility to readability: Recovering the ink of Herculaneum. PLoS ONE. doi:10.1371/journal.pone.0215775
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “From invisibility to readability: Recovering the ink of Herculaneum” (2019)
[3] Lai (2022). Generating Grid Multi-Scroll Attractors in Memristive Neural Networks. IEEE Transactions on Circuits and Systems I Regular Papers. doi:10.1109/tcsi.2022.3228566
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Generating Grid Multi-Scroll Attractors in Memristive Neural Networks” (2023)
[4] Arena (1996). Generation ofn-double scrolls via cellular neural networks. International Journal of Circuit Theory and Applications. doi:10.1002/(sici)1097-007x(199605/06)24:3<241::aid-cta912>3.0.co;2-j
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Generation ofn-double scrolls via cellular neural networks” (1996)
[5] Yu (2022). Privacy Protection of Medical Data Based on Multi-Scroll Memristive Hopfield Neural Network. IEEE Transactions on Network Science and Engineering. doi:10.1109/tnse.2022.3223930
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Privacy Protection of Medical Data Based on Multi-Scroll Memristive Hopfield Neural Network” (2023)
[6] Zhang (2020). Initial offset boosting coexisting attractors in memristive multi-double-scroll Hopfield neural network. Nonlinear Dynamics. doi:10.1007/s11071-020-06072-w
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Initial offset boosting coexisting attractors in memristive multi-double-scroll Hopfield neural network” (2020)
[7] Tang (2023). Dynamics analysis and hardware implementation of multi-scroll hyperchaotic hidden attractors based on locally active memristive Hopfield neural network. Nonlinear Dynamics. doi:10.1007/s11071-023-09128-9
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Dynamics analysis and hardware implementation of multi-scroll hyperchaotic hidden attractors based on locally active memristive Hopfield neural network” (2024)
[8] Wan (2023). Symmetric multi-scroll attractors in magnetized Hopfield neural network under pulse controlled memristor and pulse current stimulation. Chaos Solitons & Fractals. doi:10.1016/j.chaos.2023.113259
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Symmetric multi-scroll attractors in magnetized Hopfield neural network under pulse controlled memristor and pulse current stimulation” (2023)
[9] Zhang (2024). Multidirectional Multidouble-Scroll Hopfield Neural Network With Application to Image Encryption. IEEE Transactions on Systems Man and Cybernetics Systems. doi:10.1109/tsmc.2024.3489226
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Multidirectional Multidouble-Scroll Hopfield Neural Network With Application to Image Encryption” (2025)
[10] Li (2024). Symmetric multi-double-scroll attractors in Hopfield neural network under pulse controlled memristor. Nonlinear Dynamics. doi:10.1007/s11071-024-09791-6
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Symmetric multi-double-scroll attractors in Hopfield neural network under pulse controlled memristor” (2024)
[11] Lin (2022). Generating n-Scroll Chaotic Attractors From a Memristor-Based Magnetized Hopfield Neural Network. IEEE Transactions on Circuits & Systems II Express Briefs. doi:10.1109/tcsii.2022.3212394
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:02 PM UTC · the registry holds “Generating <i>n</i>-Scroll Chaotic Attractors From a Memristor-Based Magnetized Hopfield Neural Network” (2023)

Review

Not peer reviewed. No human scientist has reviewed this survey. Its template and landmark summaries were written with an AI assistant (Claude); the papers it lists are real and each was checked at its registry, so anyone can follow the links and read them.

Each listed DOI was resolved, and its title, year and first author matched the listing.
Each work the search found is held by Crossref, a registry independent of the search.
Each number in the headline and summary is accounted for by a listed claim.
Not shown: 1 candidate work(s) whose registry record did not confirm them (10.1142/9789812567741 mismatch).

Code version: deb216f03447

What the record does not say

This survey lists what each paper reports; the game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited.

How this was written

Landmark works named by the desk, then the most-cited works with a DOI that OpenAlex returns when titles and abstracts are searched for (Herculaneum OR papyrus OR papyri OR scroll OR "virtual unwrapping") AND ("machine learning" OR "deep learning" OR "neural network" OR "neural networks" OR "artificial intelligence" OR convolutional OR "reinforcement learning" OR "language model" OR transformer); a hit is kept only if its own title names the field and its title or abstract names an AI method, as whole words, and the hits that name the most of these words in their title come first. Each candidate was looked up at Crossref (OpenAlex as second resolver) and its title, year and first author compared; a work the search found is shown only when Crossref holds it. Landmark summaries were written by the desk; the other works are listed by their own titles.

Source records: code:src/lib/world-grammar/place-grammar.ts#resolvePurpose · doi:10.1126/sciadv.1601247 · doi:10.1371/journal.pone.0215775 · doi:10.1109/tcsi.2022.3228566 · doi:10.1002/(sici)1097-007x(199605/06)24:3<241::aid-cta912>3.0.co;2-j · doi:10.1109/tnse.2022.3223930 · doi:10.1007/s11071-020-06072-w · doi:10.1007/s11071-023-09128-9 · doi:10.1016/j.chaos.2023.113259 · doi:10.1109/tsmc.2024.3489226 · doi:10.1007/s11071-024-09791-6 · doi:10.1109/tcsii.2022.3212394