Pitch Black Industries · Phdpaper · Method

The
Instrument

DNAGenomicsGPT v7.10.
Built on the assumption that its own output
will be cross-examined.
Therefore built to refuse.
01 · The problem it was built for

A psychiatry shortage meets a courtroom

A person in a psychiatric crisis enters the justice system. A defence needs a forensic psychiatric assessment. There is a waiting list measured in months, a shortage of qualified assessors, and a hearing date that does not move.

That gap is the entire reason this system exists. Not to replace the forensic psychiatrist, which it cannot do and does not attempt. To produce the structured evidentiary groundwork the psychiatrist would otherwise spend weeks assembling, so that scarce expert time is spent on judgement rather than on compilation.

The intended readers were named at design time and the whole architecture follows from them: psychiatric tribunals and courts, magistrates and public prosecutors, emergency and medical personnel who need to know how to help someone quickly, mental health professionals deciding where to focus, and forensic or defence legal teams trying to understand a client.

Every one of those readers is either adversarial or operating under time pressure. Design for that reader and you get a very different machine than the one you get from designing for a curious consumer.

02 · Scale

What goes in

600,000+SNPs
Consolidated from multiple raw consumer-genomics sources. One subject file measured 609,346 markers. CircleDNA exports arrive split across roughly thirteen volumes totalling about a gigabyte.
31Mpoints of exome data
Whole exome sequencing layered on top of the array data, giving coverage the consumer panels alone cannot reach.
50,000words of instruction
The instrument itself: roughly 150 pages of triple-audited specification, plus 105 sequential operator prompts that drive a single evaluation from first contact to signed conclusion.
200-400pages out
Structured for forensic and clinical review rather than for reading pleasure. Cover letter, contents, executive summary, then the domains, then the full SNP trace table, then triage and legal summary.
03 · The design principle

Built to refuse

Most systems in this category are built to produce an answer. This one is built to decline to produce one, wherever the data does not support it.

That inversion is the whole contribution, and every constraint below exists because a hostile cross-examination would otherwise find it.

No imputation
If a variant was not genotyped in the subject's raw file it is marked absent and excluded from scoring. It is never estimated from neighbouring markers, never inferred, never quietly filled in.
Coordinate conversion is mandatory
Some sources report rsIDs, some report chromosome and position only. Position-only markers must be resolved to rsIDs against a reference map before evaluation. Skip that step and you generate false negatives, and a report with false negatives in it is inadmissible.
Traceability per volume
Every result carries the source file it came from. A reviewer can walk any single line of the report back to the raw byte it was derived from.
Coverage normalisation
Consumer panels do not carry every psychiatric locus. Scores are normalised against markers actually present, so partial coverage produces a correctly weakened result rather than a falsely reassuring one.
Zygosity weighting
Homozygous risk alleles carry double weight, heterozygous single. Protective and neutral genotypes are struck through and removed from the risk total rather than silently dropped.
Mandatory self-audit
Every two to three blocks the system halts and requires the operator to confirm that every marker shown was read from the subject's raw data and that nothing was inferred. It will not continue without that signal.
An instrument that cannot say "not enough data" is not an instrument. It is a generator.
04 · Evidence base

Where the numbers come from

Nothing in the output originates with the system. Every marker used is drawn from published, peer-reviewed association work, and the report names the source for each one so that a reviewer can check it independently.

Primary association data
Psychiatric Genomics Consortium, the GWAS Catalog, and the primary genetics literature.
Variant annotation
dbSNP for identity and context, ClinVar for clinical significance, SNPedia for trait annotation.
Functional interpretation
GTEx for expression in brain tissue, eQTL mapping, and chromatin state from large-scale epigenome projects. A variant that does nothing in neural tissue is reported as such.
Scale example
Schizophrenia alone runs against a validated list in the low hundreds of markers, each one checked, matched and reported individually rather than collapsed into a single score. HIGH · list size moves with each GWAS release

Polygenic risk is reported as a percentile against a reference population and as a relative multiplier against baseline. It is never reported as a diagnosis, because it is not one, and the report says so on its own first page.

05 · Limits

What this instrument cannot do

It cannot diagnose. Polygenic liability is probabilistic. A high percentile is a statement about a population, not about a person's condition, and certainly not about their conduct.

It cannot establish intent. No sequence of base pairs speaks to what somebody meant to do. A report that is read as though it did would be a misuse of it, and the cover letter exists to prevent exactly that reading.

It cannot separate gene from environment. Expression depends on circumstances the genome has no record of. Trauma, poverty, injury, and the ordinary accidents of a life are not in the file.

It cannot cover what was never measured. Consumer arrays sample the genome, they do not read it. The coverage figure printed beside every domain is there so nobody mistakes a partial panel for a complete one.

It has not been externally validated. This is a method paper describing an instrument in use, not a clinical validation study. That study has not been run, and until it is, the honest status of this work is promising and unproven. Stated plainly rather than buried

06 · Provenance

Where it sits

DNAGenomicsGPT v7.10 was designed and built from scratch by Rio Ezra Kho, and predates the research programme it now sits inside. It is the origin instrument of the blackpaper line, which concerns suicide reduction, and it is the technical basis of the accelerated postgraduate research proposal that line grew out of.

The full instruction set and the 105 operator prompts are held privately. They are the working apparatus rather than the argument, they carry commercial value, and any real evaluation contains a specific living person's psychiatric and genomic profile. Subject material is never published, in whole or in part, under any circumstances. Access to the method for research or clinical collaboration is available on request under agreement.

07

The point

Somebody in a cell tonight is being assessed by a system with no waiting list, no notes, and no genome. The instrument does not fix that. It shortens the part a machine can honestly shorten, and refuses the part it cannot.

Complement the psychiatrist. Never replace them. Never pretend to.
Cognitive Intelligence Services Pty Ltd · ABN 42 689 181 208
Sydney, New South Wales, Australia

Companion to the blackpaper on suicide reduction, the whitepaper on neurodivergence, the greenpaper on poverty reduction, and the redpaper on variance.

Not legal, medical, or diagnostic advice.