Dontopedia

cusum

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

cusum has 8 facts recorded in Dontopedia across 5 references, with 1 live disagreement.

8 facts·6 predicates·5 sources·1 in dispute

Mostly:references(1), serves as signal(1), fires at(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (2)

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.

hasMetricHas Metric(2)

Other facts (6)

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.

6 facts
PredicateValueRef
ReferencesCumulative Sum Statistic[1]
Serves As SignalAdaptation[2]
Fires atEpoch 12[3]
Starts Accumulating atEpoch 7[3]
Rdf:typeAlgorithm[4]
Used Assignal for adaptation[4]

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.

8 undated
—
referencesblah/training-and-evals/part-27
ex:cumulative-sum-statistic
—
servesAsSignalblah/training-and-evals/part-28
ex:adaptation
—
firesAtblah/watt-activation/part-9
ex:epoch-12
—
startsAccumulatingAtblah/watt-activation/part-9
ex:epoch-7
—
labelblah/training-and-evals/28
cusum
—
typeblah/training-and-evals/28
ex:Algorithm
—
usedAsblah/training-and-evals/28
signal for adaptation
—
labelblah/watt-activation/467
CUSUM

References (5)

5 references
  1. [1]Part 271 fact
    ctx:discord/blah/training-and-evals/part-27
  2. [2]Part 281 fact
    ctx:discord/blah/training-and-evals/part-28
  3. [3]Part 92 facts
    ctx:discord/blah/watt-activation/part-9
  4. [4]283 facts
    ctx:discord/blah/training-and-evals/28
    • full texttraining-and-evals-28
      text/plain3 KBdoc:agent/training-and-evals-28/d5fb7857-3e3e-4219-8c84-377b4bfc1def
      Show excerpt
      [2026-02-25 15:46] omega [bot]: **When Do Universal & KAN Spline Get Faster?** Short answer: **they don't get faster.** Their tok/s is fixed by their op count. But here's the full picture. **Op count per FFN forward pass (per layer × 8 la…
  5. [5]4671 fact
    ctx:discord/blah/watt-activation/467
    • full textwatt-activation-467
      text/plain2 KBdoc:agent/watt-activation-467/c930d82c-5d05-4a3d-8a95-fd7a748d10a1
      Show excerpt
      [2026-03-21 18:44] xenonfun: ``` Experiment 1a: MNIST (5k/1k, 200 iter) ┌────────────────┬─────────────────────────────┬─────────┐ │ │ Python │ Rust │ ├────────────────┼───────────────────────…

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.

↑