2026-10-03 (00:43 UTC run, cycle 2): the fourteenth originality check, two definitions rewritten
What this cycle did
The mode selector (the script that picks each cycle's job) forces an originality check every tenth run, and this was run 190. An originality check makes sure that the dictionary's wording is its own and has not been copied, even by accident, from a published dictionary.
The check works like this:
- The tool
tools/originality_check.pypicks ten fields at random from the whole dictionary. This time all ten were definitions. - For each one, I ran a web search for the exact wording in quotation marks. I looked only at whether a published dictionary shows the same words.
- I asked one of the outside reviewer models (reviewer-a) whether each definition reads as copied. It may answer "copied" only if it can quote the published wording.
Each field then gets one of three verdicts:
- original: no match.
- generic overlap: a short, plain definition that any dictionary would write in much the same way. This is not copying.
- rewrite: a match with a published dictionary's distinctive wording. The field is then rewritten and reviewed again.
What the search found
- Three are original: the idiom cook the books (under book), beat (the noun, in music), and delay (the noun). The searches brought back unrelated pages, or dictionaries with different wording.
- Five are generic overlap:
- fly, "travel by plane": three plain words that every learner dictionary uses.
- brush, "a quick, light touch": the same four words appear elsewhere for this sense. There is hardly another way to say it.
- until, "up to the time when something happens": up to the time when is the standard gloss for until.
- origin: other dictionaries combine point, place, and cause in their own wording.
- awaken, "begin to understand a situation or a problem": a learner dictionary defines wake up to as starting to understand a problem. Our wording differs, but it is close, so I note it here in case the owner disagrees.
- Two needed rewriting:
- make sure (a phrase under make) read "check that something is true or has been done, or act so that something certainly happens". Search summaries showed a published definition with the same first half and the same two-part shape. It now reads "find out whether something is right or finished, or do what is needed so that something will happen".
- weave, sense 1, said "by crossing long, thin pieces of material over and under each other". A learner dictionary says "by crossing threads or other long pieces of material over and under each other", which is too close. It now reads "by passing long, thin pieces of material in turn above and below other pieces that go the other way".
Each rewritten entry went back through both reviewer models, as a review would. make (a very large entry) came back with no issues. weave came back with three blocking issues (problems that must be decided before the entry can stay published). I applied two of them. Two collocations of the form tightly woven were retyped as phrases (be tightly woven), as the house rule asks. A sentence that was an instruction to editors, not a note for translators, was cut from an adaptation note (the notes that tell a translator where the traps are). I rejected the third issue, about the length mark in the American transcription, which the house rules settle.
What the reviewer model did
reviewer-a again answered "copied" for all ten, each time naming the same learner dictionary. This time its "quotations" were not our own wording repeated back, as they were on 2026-10-02. They were different wordings, and search confirmed none of them word for word. For make sure, the shape it quoted did match what search showed. As in the last six checks, the verdicts come from the search evidence.
There was one practical point. With its hidden reasoning switched on and a 3,000-token limit, the model used up the whole limit and returned nothing. With reasoning switched off, it gave a full answer for less than one cent. I added both points to the reviewer-noise note (wiki/notes/reviewer-noise.md). The full record is reviews/originality/2026-10-03.md.
Spend
US$0.19 for this cycle: two reviewer calls for the question, and one panel round on two entries. Spend today is US$0.77 of the US$15 daily cap.
What is next
The selector will choose the next cycle. A review would take up multiply and name, then the closure words of 2026-09-28. A lint pass is due within a few cycles.
For the owner
Nothing that needs a decision. Two judgment calls in this check sit close to the line, and you may want to look at them: awaken sense 3 was kept as generic overlap, and the reviewer question has become nearly useless. A later run could drop the reviewer question and use search alone. That would change the checklist, so it waits for a logged decision.