How thirteen agents read one fixture
Each pass has one job and cannot see the others. That independence is what stops one confident mistake becoming the assessment.
The research half of an assessment is not one long read. It is thirteen short ones, each with a single question, each blind to what the others found.
Why blind
A single reader who has already decided that the home side is undercooked will read the next article looking for that. It is not dishonesty, it is how reading works, and it is why one pass with a strong prior produces an assessment that is confident and narrow.
Thirteen passes that cannot see each other cannot do this. When eleven of them find nothing and two find the same injury independently, that is a real signal. When six find one thing and seven find the opposite, that is also a real signal, and it says the fixture is less knowable than it looked.
What the disagreement is worth
The tempting move is to resolve a disagreement by weighting the more confident pass. That is exactly wrong. Confidence in a research pass mostly measures how emphatically a source was written, and the emphatic sources are the ones with an audience to hold.
So disagreement is kept. It widens the interval on the final number, which usually pushes the composed probability back toward what the fitted model said, and that is the correct behaviour: when we do not know, the honest answer is the base rate.
The failure this does not fix
Independence between passes does not create independence between sources. If every outlet is working from the same agency wire, thirteen blind passes will find the same claim thirteen times and it will look like overwhelming agreement. Checking whether sources are actually distinct is a separate problem, and it is the one this design is weakest on.
What this does not tell you
Nothing here says the passes are right. They are a way of failing less correlated, not a way of being correct, and a fixture nobody has written about returns thirteen empty hands.
Common questions
Why thirteen separate passes instead of one?
Because a single pass that has already formed a view reads later evidence to confirm it. Independent passes cannot do that, so a disagreement between them is real information rather than noise.
What happens when two passes disagree?
The disagreement is kept and widens the uncertainty on the final number. It is not resolved by picking the more confident one.
Do the passes share their findings?
No. Each runs blind to the others, and they are only combined at the end. Letting them see each other would collapse thirteen views into one.