Every file, readable here
The files behind the papers
What is here
For each mathematics manuscript: the PDF and its LaTeX source, its figures, its reviews with written answers, and every checker, a program that recomputes the paper's numbers, beside the output it recorded. The dividing-plane note adds a ledger, a move-by-move account of the OpenAI forced Navier-Stokes blow-up manuscript, and explanations of its sections.
How to read a review
Each manuscript had four reviews by named AI models, numbered in order: two by the other company's model and two by models of the writer's company in fresh sessions. In file names, cross-review and self-review mark the first of each kind. Written answers say what changed, finding by finding. Reviews keep the project's internal names and are published as delivered, with one exception: one line of one review, naming a private folder, is withheld from its public copy and marked where it stood.
What you can rerun, and what to do with what you find
- The antiunitary paper's
verify.py, with the listed library versions, andverify_exact.py, with only Python's standard library. - The Gil note's
verify_gil.py, about four minutes. - The dividing-plane note's
midplane_barrier.py, about one second; its tests load it from a private path and so do not run here. - The unfolded-zeros paper's
verify_identity.pyandverify_kadec_1e5.pycannot be rerun: they read an unpublished table of zeros; their outputs are here.
The owner would like to know what you make of these papers. A few words are enough: right, wrong, known, minor, worth a look, or not your area. In his words: "If it is right I want it in the record." If it is wrong, the page is corrected the same day and you are told; if it is already known, the page credits the earlier work.
Write to david@hypnosmath.org. He reads and answers replies himself; an error you find is fixed in the published files and on this site the same day, and you are told; nothing you send is given to any AI model without your permission.
The five papers and their origins
-
Approximate Antiunitary Symmetry as a Matching Problem
Its motivation is five notebook entries of late September: two the judge wrote on small-model lines (one a recall of the classical fact that a skew-symmetric matrix of odd order has determinant zero, one a false conjecture) and three results of programs. The paper calls them motivation, not premises; its main theorem is a reformulation the writing session made; no source is recorded for its key tool, the matching polytope.
-
The unfolded zeros of the Riemann zeta function do not form a Riesz basis of exponentials
The only one whose chain begins with a small model's own line: a ten-word recall of Kadec's theorem on August 12, 2026, kept by the judge as a question; more lines and sharper judge-written questions over five weeks; ten programs; on September 28 a session the owner started scored six chains of entries and chose this one; the paper says its main theorem answers the question the notebook posed.
-
Maximal Coherence for Prescribed Intrinsic Populations and Youla Values: Two Questions of Gil
The two questions are J. J. Gil's own, from Entropy 28(8):877 (August 4, 2026). They surfaced while frontier models reviewed the antiunitary paper; GPT-6 Astra's own review proved the free-value answer first. No step of the note's mathematics came from the harness.
-
A dividing-plane barrier in the OpenAI forced Navier-Stokes blow-up construction
A separate line of work the owner ran with frontier-model sessions on the OpenAI manuscript: Claude Opus sessions wrote section digests and eleven section explanations, from which a Claude Fable 5.1 session assembled a ledger of the construction's moves; the explanation of Appendix B asked the question and sketched the answer; a Claude Fable 5.1 session ranked it first on its map of open questions and proved it. No small model's line is among its sources, and the material has not been filed into the notebook.
-
It reports on the harness's own conduct, not on mathematics.
- SHA-256
07adc64f3bf73ab29a42214a8bd33e099fb8eecdee0eb4c9beb8dadfb5b15be5
The same files on GitHub
The public repository github.com/dross50/hypnos-papers holds every file here at the same path, with the same SHA-256, a fingerprint of its bytes; each paper's PDF sits at its top level.