FedSym Full (thresh=96)
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
FedSym Full (thresh=96) has 14 facts recorded in Dontopedia across 1 reference.
Mostly:has parameter count(1), has accuracy metric(1), has accuracy std dev(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (1)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
manifestsInManifests in(1)
- Compression Effect
ex:compression-effect
Other facts (13)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Has Parameter Count | 86000 | [1] |
| Has Accuracy Metric | 0.878 | [1] |
| Has Accuracy Std Dev | 0.005 | [1] |
| Statistically Better Than | Fedprox Ft | [1] |
| Has P Value | 0.009 | [1] |
| Has T Statistic | 4.78 | [1] |
| Has Cohens D | 2.14 | [1] |
| Wins Count | 5 | [1] |
| Total Wins | 5 | [1] |
| Parameter Multiplier | 1.6 | [1] |
| Uses Less Total Communication Than | Fedprox Ft | [1] |
| Communication Volume | 220000 | [1] |
| Communication Round Count | 1 | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (1)
ctx:discord/blah/watt-activation/429- full textwatt-activation-429text/plain3 KB
doc:agent/watt-activation-429/b18dc08f-4e77-4134-ab4f-183a2f544d75Show excerpt
[2026-03-20 03:23] lisamegawatts: Done — 7 pages, clean compile. The paper is fundamentally rewritten: Old narrative: "Block-diagonal fusion beats FedAvg by +3.5pp" New narrative: "Block-diagonal alone is a capacity confound. The full evol…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.