Beyond the text layer.

Converted, the text travels and the pictures do not, so anything said about a drawing is generated rather than extracted — a claim, not an extraction. One thread runs through what follows: the conversion record — including the hash this engine does not take — which continues, with the ledger of what is open, in Paper 004. This paper sets out what would have to be true before such a claim reaches a model, and what would count as a result.

§1What the model was shown, six months later

An organisation runs a supplier's drawing pack through a document pipeline, a model reads the result, and a compliance summary quotes a tolerance from it. Six months later the part fails, and someone who owes the organisation nothing asks what the model was shown. Not the drawing — the bytes. Where nothing was recorded, the honest answer is a filename and a date, which is a claim.

Conversion is an event, and it can be recorded like any other. What exists today is more than nothing and less than a record: the sha256 of the source bytes, the converter and its risk rung where one ran, the OCR provider, its egress and a status per page — and no page text, since an audit record carrying the document defeats its purpose.

Three things are absent. No engine-version field appears in the documented response; nothing points a derived statement back to the pixels; and the output side is unhashed — the bytes that went in are fingerprinted, the Markdown that came out is not.

§2OCR reads the glyphs, not the picture

The text a reader sees is one layer of a PDF; figures, scanned annexes, drawings, charts and photographs sit outside it. A picture becomes a figure block holding its position, carrying a caption only if one was printed beside it, never one the engine wrote. A page uploaded natively arrives as an image and its text, which is what lets a reader ask the model about its charts;^[1] the converted page cannot be asked, and that is what conversion gives up.

OCR does not close the gap, because it reads glyphs rather than pictures: over a schematic it recovers the labels and leaves the schematic. The provider is handed a raster rather than the document — rasters in, lines out — and each line is capped at inferred, because certain means the format said so. The difficulty is not local to one engine: a 2026 benchmark on engineering drawings reports models reading a drawing's text far more accurately than its symbols, and calls symbol-centric understanding unsolved^[2] — the authors' word, on their own preprint.

A merged cell has no representation in the Markdown emitted^[3] — Paper 001 §4 gives the specification — so the cell is flattened and the table named in a warning. The tolerances citable from a drawing are those that were in a table, and not all of even those.

// the two sentences that came out newly false
"The longest thing in your estate goes in whole."
"…the tolerances you can cite are the ones that were in a table,
   and they are all of them."

// what the checks returned
type checker · test suite · claims diff → PASS

// what was true, one panel away on the same page
the window decides what fits, and intake caps at 2,000 pages
a merged cell is flattened, so a table can lose a tolerance

Absolutes arrive during positive rewrites, and the strongest sentence in a rewritten section is the likeliest to have overshot.

§3A picture is a claim waiting to be made

Knowing what is in a picture is several jobs wearing one name: reading values off a chart, recovering the instruments and connections of a piping and instrumentation diagram, following a floor plan or an assembly drawing, naming what a photograph of a site shows. They are one kind of thing — every one of them is generated — and they differ sharply in difficulty and in whether anyone can score them.

Extraction is deterministic and checkable; description is generated and is a claim. The same bytes give the same Markdown — asserted in the engine's documentation rather than demonstrated by a published corpus, as Paper 004 §4 records — so a doubter can convert the file again and diff. A description cannot be re-run that way: a second run may write another sentence, and either may assert what is not in the picture. A 2018 study found captioning models "prone to 'hallucinating' objects that are not actually in a scene", and a 2023 study finds the current model class inherits it.^[4]

One vendor's documentation instructs that image interpretations be verified.^[5] So a description reaching the model is labelled as derived, kept below certain — OCR lines are capped at inferred, and a generated sentence has no claim to sit higher — and carries a way back: page, bounding box and the sha256 of the raster. It exists only where the pipeline owns the rasterisation: a natively uploaded PDF is rasterised server-side "at dimensions you don't control", so the coordinates that come back cannot be reliably mapped onto the page. A caption so recorded is locatable, not true.

A derived statement needs its provenance committed with it, and committed injectively: caption, page, box and hash run together by plain concatenation let whoever writes the record move the boundary between them — the defect Paper 002 of The Project Handshake found in its own leaf encoding. A verifier checks the box against the raster, not the sentence against the picture.

§4What is being researched, and what would count as a result

The direction under research is an enhancement tier over the deterministic baseline, and none of it is built: the engine accepts the option today and ignores it. It would act only on blocks already flagged as needing help — figure alt-text, chart-to-table, reconstruction of flattened merges, semantic chunk boundaries — marking each touched block enhanced: true, returning the deterministic output byte-identical when the tier is off, aborting to it at a cost ceiling, and routing model calls through a gateway with an evidence log.

The difficulty is evaluation, and it is uneven:

A piping and instrumentation diagram is drawn in a vocabulary — ANSI/ISA-5.1-2024 establishes "a uniform means of designating instruments and instrumentation systems used for measurement and control"^[8] — and a vocabulary invites structured output rather than prose: node and edge lists, tag-to-value statements, each carrying its box and raster hash. A result would be a measurable margin over the baseline on a corpus with ground truth, and for an estate's own drawings no such corpus exists: the published benchmarks are other people's documents, and annotating an estate's own is work that would have to be paid for before anything could be scored. Marked open, all of it.