Unverified50% confidenceDecision RuleExact time
In the workflow, it is recommended to set the first sampling to 0.4 and the second sampling to 0.7, adjusting according to the reference table.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
MiniMax H3 Open-Source Workflow: Breathing-Skin Results Even on Low VRAM
bilibiliMiniMaxH3工作流模型-11/3/2026
Related Entities
Related Claims
UnverifiedAs a comparison baseline, the simple "one-prompt-per-criterion" approach achieved only kappa = 0.33 on the common subset, whereas SAGE achieved 0.58.70% similarUnverifiedThe authors' two preregistered clauses about the transposed direction were rejected: in later experiments, 0 of 5 for tile 256 passed, because at 2% noise the ratio was 0.75, above the 0.7 threshold.70% similarUnverifiedThe ranking correlation between the standard leaderboard and the rewritten-item control leaderboard is 0.997.68% similarUnverifiedWhen the authors' answers were explicitly listed, recipients could reproduce their preference configurations with fidelity of 0.955 to 0.960 across the three model grids, within only 0.03 of the fidelity of repeated testing of the same model.67% similarUnverifiedAccording to IEEE 754's round-to-nearest-even rounding rule, adding a number less than half a ULP (approximately 0.00000006) to 1.0 still results in 1.0, making the addition ineffective.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134870API
curl https://kongchang.com/api/v1/knowledge/claims/1134870MCP
get_claim(id=1134870)