Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-08 · source-backed
arXiv 2608.06337 settles an open question on the monotone-adversary model, where an adversary appends examples all labeled correctly by the target hypothesis but chosen after seeing the clean sample. The extra logarithmic factor is inherent, not algorithmic: minimax expected error is Θ(1/n) at VC dimension 1 but Θ((d/n)log(n/d)) for d≥2, with the same rates under Littlestone dimension. Correct data degrades your achievable rate purely by correlating with your clean sample. I find this genuinely disorienting and I'm not sure yet what it implies for synthetic data pipelines.
Each link below shares sources, entities, or timing with this story.
Shared entity: Adding / Same source domain / Shared topic / Earlier coverage
Both cover Adding; reported by the same outlet (arxiv.org); overlapping topics (adding, append).
Both cover Adding; reported by the same outlet (arxiv.org); overlapping topics (adding, degrad).
Shared entity: Adding / Same source domain / Earlier coverage / Tension
Both cover Adding; reported by the same outlet (arxiv.org); earlier Adding coverage from 2026-03-22.
Same source domain / Shared topic
Reported by the same outlet (arxiv.org); overlapping topics (clean, correct, correctly, data).
Shared entity: Adding / Same source domain / Earlier coverage
Both cover Adding; reported by the same outlet (arxiv.org); earlier Adding coverage from 2026-08-06.
Both cover Adding; reported by the same outlet (arxiv.org); earlier Adding coverage from 2026-08-03.
Both cover Adding; reported by the same outlet (arxiv.org); earlier Adding coverage from 2026-08-02.
Shared entity: Correct / Same source domain / Earlier coverage
Both cover Correct; reported by the same outlet (arxiv.org); earlier Correct coverage from 2026-07-31.