Weights that ignore difficulty: a cross source derivation weighted like a direct read, or one operation at 5 in one row and 3 in the next.
Do this instead
Weight by axis count, never importance. A lookup at 5, or a chained derivation at 1, is a two level miss.
Where it happened
One real task. Each shows the spot and what it should have been; click any line to open the task there.
the words at faultthe row or field at faultmissing from the taskwhat is righta task file
Example 18Small Business & Personal Docs · 3 Leg A turns
What is wrongObjective criterion 12, the BendFilm fee worked out from a ticket order, weighs 1, like objective criterion 17, a page count read off the inventory. A calculation from one source takes +3.
Leg A turn 1 sets the BendFilm fee at four times the order processing fee of the June Timbers vs Sounders game: $5.00 on the Ticketmaster order, so $20.
In vantol_films_2026_submission_dashboard.html, the BendFilm Festival fee is shown as $20.worked out: the June game's order found, its fee read, times four
In vantol_films_2026_submission_dashboard.html, the RACC project treatment associated with SetInLead_Treatment_Final.pdf is classified as Ready.one read: the treatment PDF's page count
How it breaks the standardObjective criterion 12 takes a hidden field and a calculation: find that order, take its order processing fee rather than its $15.00 service fee, and multiply by four. Objective criterion 17 checks one listed page count against a limit. At 1 each, a Model A run that misses the fee loses no more than one that misreads a page count.
The rule it breaksGuidelines · 5.2 Rubric WeightsWeight is difficulty, never importance.Priced by four axes (source coordination, reasoning depth, modality, discovery effort): three or more is +5, two is +3, zero or one is +1.
Criteria that are objectively incorrectly weighted by two levels, e.g., 1 is selected when 5 is appropriate or vice versa.
A Moderate issue, despite its name.
Why it matters
The scale exists to separate discovery from lookup. When it does not, the final score says nothing about whether the model did the hard part, and a run that nails every lookup while missing every derivation still scores well.
Hey, Idris here. I have been trying to get a clearer handle on the grant and festival submissions because the information is spread across different places, and I do not want to keep checking separate notes every time I need to confirm information about them. I have been bouncing between project files, old planning notes, festival records, and submission paperwork, and a couple of newer records I found, and at this point I would rather have one place that I can actually trust when I need to see what is due, what each opportunity is asking for, what we already have on hand, and whether the versions we have can actually be submitted. I have attached the dashboard and records to the workspace, so please populate the submission overview for the RACC project, Big Sky, and BendFilm with each opportunity's project or film, deadline, fee, and notification date or window, and complete the requirements section for all three. For each item, classify it as Ready, Needs adaptation, or Missing, and show the relevant file when there is one. For the fees, they have confirmed to me that for RACC it will be the same amount as the service fee from the Timbers vs Sounders game in June, and that for Big Sky it will be twice that service fee. For BendFilm, it will be four times the order processing fee from that same game. I also found a festival message and a runtime record, so please reconcile them with the rest of the available records and update anything that is no longer accurate. I also need the runtime section completed so I can see whether Slack Tide actually qualifies for each one. Please base the calculations on the timecodes and use the displayed values directly. Please save the updated dashboard as `vantol_films_2026_submission_dashboard.html`.