WRSWorld Research StateContribute
WORLD RESEARCH STATE

OpenAI: A matrix-multiplication exponent at most 9/4

Reported result · significance if the exact claim is established

If verified · conditional significanceClaim scope and evidenceReported result · not independently verified.
If verified · reference score600,000Editorial revision range 350,000–850,000. Not a statistical interval. Included in rankings as an unverified reported result; excluded from achieved-science progress totals.

Provisional assessment of the stated contribution scope. Scientific evidence and contributor attribution are separate.

Scientific record data (JSON) · Challenge or correct a rating

What is claimed?

For every epsilon>0, the paper claims multiplication of n-by-n complex matrices in O_epsilon(n^(9/4+epsilon)) scalar arithmetic operations, hence omega(C)<=9/4.

Scientific scope

The statement has exponent slack and is over C. It is not an unconditional O(n^2.25) practical running-time guarantee, an omega=2 solution or a measured GPU speedup. The family formalization note selects other companion paths. WRS inspected the selected opening statement and available scope note, not the full proof; independent formal replay was not run.

Evidence state

The manuscript reports a proof. WRS has not independently audited the complete argument or replayed the reported formalization. The grade and score here express conditional significance; they do not certify correctness. The provisional value enters the main reference rankings with an unverified label, but not achieved-science progress totals.

Full scientific record · Challenge or correct this assessment