No automated system has produced a proof requiring a definition absent from its training library, across 11 documented research-level attempts
[unresolved]
[no evidence]
[quiet]
[stable]
[undecided]
A 2028 survey by Nakashima, Prieto & Osei catalogued every publicly reported attempt to attack an open research problem with an automated prover. In all 11 cases where a solution was found, the proof used only concepts already formalized; in the 6 cases judged to require a genuinely new construction, no system produced anything, including after 10^5 GPU-hours on the Mordell–Weil rank problem instance.
Accurate
(+0)
Falsifiable
(+0)
Clear
(+0)
Novel
(+0)
Important
(+0)
▸ Score Details
Cited as evidence in 1 claim:
By 2035 a machine-generated proof of a previously open Anna…
(opposes)
cited by (1)
cited as opposes by:
[+0]
By 2035 a machine-generated proof of a previously open Annals-level conjecture will be formally verified in Lean and accepted without a human-written proof sketch
ai-forecasting
formal-verification
mathematics
virtues: Accurate unrated · Falsifiable unrated · Clear unrated · Novel unrated · Important unrated
this claim:
No automated system has produced a proof requiring a definition absent from its training library, across 11 documented research-level attempts
supports (0)
no supporting evidence yet
Evidence Supporting (0)
No supporting evidence yet.
Evidence Against (1)
The 2028 survey's six 'requires new construction' problems were rated by refere…
Undermines the parent's central classification rather than its data collection, which matters because the survey's force comes entirely from the 6-case negative set. If a third of that set is misclassified, the barrier to concept invention looks lower. The counter is that two of four were confirmed, so the effect is attenuation, not reversal.
0 supporting / 1 opposing
Respondeo
Loading responses...
Log in to join the discussion.