Two thirds of what has been read has never been written up. That gap, not the reading, is what keeps RA out of the guide.
Reading is nearly done and nothing has been written up, because no sweep has been defined for it yet. That is a decision, not a delay.
Plus 25,473 other posts in the same manifest, assigned to nobody.
1,019 of those readings carry one line of substance or none. They are real files, but they will yield almost nothing when swept.
The only corpus where reading and writing up are the same act, which is why the two bars match. Six articles left.
99 Muzik issues, 3 Mixmag and 1 DJ Mag, all catalogued and dense. A sweep of all 103 was written and then reverted for quality, so the written-up bar is back at zero.
Opened the day before yesterday and barely started.
research: land Spark's twelve RA batches, 207 findings over 120 articles
15 min ago judged by its last commit
4 uncommitted change(s) in the tree.
research: catalogue Mixmag features
39 min ago judged by its last commit
10 uncommitted change(s) in the tree.
spark: RA sweep, nine overnight batches, 153 rows
30 min ago judged by file times, because this lane cannot commit for itself
Its git directory lives inside the parent repo, outside the folder the agent can reach, so it writes work it can never record. 4 change(s) are sitting unlanded right now.
1,525 articles have their page text sitting in the corpus and were never turned into a reading. 681 left only a stub saying unreadable and no page text at all, so they would have to be fetched again. 1,078 have nothing on disk whatever. Each needs a different decision and only the first is cheap.
3,360 features catalogued, 0 rows in the findings database. No sweep pass has ever been defined for this corpus the way it was for RA and DJhistory. Reading finishes in about a day and a half at the current rate, and then the lane has nothing to do.
All 103 catalogued issues were converted into 1,480 findings in one run, then reverted on quality grounds. A checking tool was written afterwards. Nobody has decided whether to run it again under that tool.
They are not features and were never part of anyone's assignment. Leaving them in the same file is what made this corpus look like a multi-year job.
Gemini writes findings into a worktree whose git directory it cannot reach. Somebody has to commit for it, every night, or the work is invisible. This will recur until the arrangement changes.
The availability check was done on 2026-09-04 and three of the twelve have been read since. The rest need you to log in to Perlego or the Internet Archive once; after that they are immediately readable.
Last code change was 2026-09-21, version v0.2.318. 50 versions shipped in the seven days before that, so this is a stop, not a slow patch.
The grouping run that produces the "no research behind it" list was made 17 min ago over 5,761 findings. There are 6,227 now, so its answer predates roughly 466 rows. Rerun it before trusting the gap list.
The last five versions:
the faces are served, and the worker stops precaching two that do not exist
the typed aside is vermillion at 14px, the toggle dropped (Joel: "b is it, drop the toggle"). Chosen on the ph
THE FLOOR IS COUNTING, BENDING IT as SVG (Joel, of the grid's staircase: "these kind of curves are what reads
B is the aside in vermillion at 14px (Joel: "14 vermillion"), one step down from v1.061's 15px with the Medium
the typed aside is a line of its own, and B is vermillion. Joel: "in the what is a dj for entry which is the t
Availability last checked 2026-09-04. Perlego and the Internet Archive both need you to sign in once; after that everything ticked below is readable immediately. Confirmed unavailable and not worth retrying: Bregman, Auditory Scene Analysis, Moore, Psychology of Hearing, Lawrence, Love Saves the Day, Fikentscher, You Better Work!.
Done on 21 September. The git history was packed, which returned 92 MB and changed nothing else. The hosted page now serves its typefaces as files instead of carrying them inlined, so a version bump no longer re-sends 422 KB; the single-file build still inlines everything, as it has to. The ledger now lists the documents it has never ingested, which previously vanished rather than reading as undecided. Those still need a sweep or a reason each, and they include the one the project instructions tell you to read before redesigning any surface:
The tool counted findings only in the main repo, so a hundred RA articles written up in the gemini lane were invisible. It now counts every worktree, and says plainly how much has not yet reached the lane that builds the guide.
It always said the index was behind. It holds 3,828 rows against 2,268 readable files, so it is 1,560 ahead of what has actually been read and 425 behind the file count. It now says which, and against what.
That sentence is a running total from batch 26. The pass stopped writing it and has since passed batch 54. A progress document appends, so a figure it stopped restating is history. The tool no longer treats one as a live claim.
The document carries a dated correction saying 96 was wrong and the manifest holds 99. It was being flagged for the error it had already fixed. A document that corrects itself is no longer counted as disagreeing.
That ledger lists 59 sources and not one of them is a corpus. It covers the documents and the banks only, 4,250 of the 6,227 findings in the database.
Subjects are what the corpus grouped itself into, by what a finding says rather than which book it came from, so a subject fed by one source is that book's shape and one fed by sixty is a real subject. That is why they are ordered by sources and not by size. Open one to read the disagreements first, then what each source says in turn. Newest is what has landed recently, dated by when a batch file last reached git, so the date is the batch's and not the row's. Guide entries is today's twelve categories, which is the structure the subjects are arguing with.