Against a two-pass hindsight scheduling oracle on the same mixed-forward backend, ASPIRE was 4.7–20.2% below oracle throughput, with 10.4% mean gap; the three long-context cells averaged 8.5%. The widest gap was Qwen3-1.7B on AIME25, and all other configurations were within 11.9%.

Against a two-pass hindsight scheduling oracle on the same mixed-forward backend, ASPIRE was 4.7–20.2% below oracle throughput, with 10.4% mean gap; the three long-context cells averaged 8.5%. The widest gap was Qwen3-1.7B on AIME25, and all other configurations were within 11.9%. · CiteArk

Measurement results

0/26 assessed

0 supported0 disputed or conflicting26 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
model: Qwen3-1.7B · dataset: AIME25	42 requests	—	Not assessed
model: Qwen3-1.7B · dataset: AIME25	2.59 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · dataset: AIME25	2.06 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · dataset: AIME25	20.2%	—	Not assessed
model: Qwen3-1.7B · dataset: LB-v2[30k-40k]	18 requests	—	Not assessed
model: Qwen3-1.7B · dataset: LB-v2[30k-40k]	4.46 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · dataset: LB-v2[30k-40k]	4.17 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · dataset: LB-v2[30k-40k]	6.5%	—	Not assessed
model: Qwen3-8B · dataset: AIME25	30 requests	—	Not assessed
model: Qwen3-8B · dataset: AIME25	1.95 × AutoRegressive	—	Not assessed
model: Qwen3-8B · dataset: AIME25	1.86 × AutoRegressive	—	Not assessed
model: Qwen3-8B · dataset: AIME25	4.7%	—	Not assessed

Against a two-pass hindsight scheduling oracle on the same mixed-forward backend, ASPIRE was 4.7–20.2% below oracle throughput, with 10.4% mean gap; the three long-context cells averaged 8.5%. The widest gap was Qwen3-1.7B on AIME25, and all other configurations were within 11.9%.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results