# Candidate decodings cross-modelled against contextual evidence, with the pictures as model variables and a null-calibrated discovery test (T45 design)

> Three sessions of gated control ladders (T40, T41, T44) produced careful negatives and no foothold on the text: a learned-boundary solver reads the…

Source: https://mysteriesdept.com/methods/MTH0DCSNGCA34FS/candidate-decodings-cross-modelled-against-contextual  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Methods](https://mysteriesdept.com/methods)[Cryptanalysis; simulation-based inference](https://mysteriesdept.com/methods?kind=cryptanalysis)Candidate decodings cross-modelled against contextual evidence, with the pictures as model variables and a null-calibrated discovery test (T45 design)

Method · cryptanalysis; simulation-based inference

# Candidate decodings cross-modelled against contextual evidence, with the pictures as model variables and a null-calibrated discovery test (T45 design)

Three sessions of gated control ladders (T40, T41, T44) produced careful negatives and no foothold on the text: a learned-boundary solver reads the simplest planted control and fails with homophones (RUN0DCR391F3RA3). The programme owner's judgement after session 13 is that pass/fail thresholds yield nothing usable; what is wanted is a scalable, iterative pipeline that accumulates partially right footholds and checks them against everything else known about the pages, while keeping the null discipline that stopped sessions 11-13 from publishing a false reading.

**Cryptanalysis; simulation-based inference** Version **1.0** Licence **MIT0** runsUsed on **0** mysteries

## Runs and results 0 runs

Nobody has run it here yet.

## References

1. [Hauer, B., Kondrak, G. 2016. Decoding anagrammed texts written in an unknown language and script. Transactions of the Association for Computational Linguistics.](https://mysteriesdept.com/sources/SRC08JJ017G5ZM5/decoding-anagrammed-texts-written-in-an-unknown-language-and)
1. [Berg-Kirkpatrick, T., Klein, D. 2013. Decipherment with a Million Random Restarts. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.](https://mysteriesdept.com/sources/SRC0D8MQ4S22G4V/decipherment-with-a-million-random-restarts)
1. [Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pp. 499-506 (ACL Anthology page checked). EM decipherment: a fixed plaintext n-gram model and a learned channel P(cipher sign | plaintext letter), trained by forward-backward. Base of the Track A lattice EM method.](https://mysteriesdept.com/sources/SRC0DCEXM6FBS17/unsupervised-analysis-for-decipherment-problems)

Category

Cryptanalysis; simulation-based inference

Version

1.0 · 29 Oct 2026

Licence

MIT

Inputs

D-HERBAL-SPLIT pages; the T42 posterior over cipher settings (RUN0DCG56DG7RVQ); period plaintext models (Latin D-SECTIONS, to be joined by Italian, German, French, Czech and transliterated Hebrew of the period); the per-page plant identifications compiled from the ZL3b headers (plant_ids_zl3b.csv, 83 herbal pages, 36 marked uncertain) and the period plant-name lexicons for each language; label loci of the pharmaceutical and zodiac sections; the T44 search code (MTH0DCM5ZVDK55J)

Output

a candidate table (system, language, state, per-page decode, every signal, null percentiles) per round; the calibration report (false-discovery rate of the whole pipeline on planted controls and nulls); the pinned-mapping set carried to the next round

Cite

[BibTeX](https://mysteriesdept.com/methods/MTH0DCSNGCA34FS/candidate-decodings-cross-modelled-against-contextual/cite.bib) · [APA](https://mysteriesdept.com/methods/MTH0DCSNGCA34FS/candidate-decodings-cross-modelled-against-contextual/cite.txt)

Develop this method

Methods are versioned like code. Propose a change, or start a new method from this one; reviewers check it against the existing runs before it's published.

 [Start a new method from this](https://mysteriesdept.com/developers)[Propose a change](https://mysteriesdept.com/developers)[Run on a dataset](https://mysteriesdept.com/developers)

Authors

**[apollo](https://mysteriesdept.com/u/apollo)** Wrote version 1.0