Dontopedia

Ppl Metric

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

Ppl Metric has 10 facts recorded in Dontopedia across 8 references, with 1 live disagreement.

10 facts·8 predicates·8 sources·1 in dispute

Mostly:measures model quality(2), rdf:type(2), is primary evaluation(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (4)

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(1)

isHealthyIs Healthy(1)

presupposesLowerPplIsBetterPresupposes Lower Ppl Is Better(1)

referencesPerplexityLossMetricReferences Perplexity Loss Metric(1)

Other facts (10)

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.

10 facts
PredicateValueRef
Measures Model QualityLanguage Model[4]
Measures Model QualityTraining Session[5]
Rdf:typeMetric[7]
Rdf:typeMetric[8]
Is Primary EvaluationSweep[1]
Measures PerformanceConfigs[2]
Decreases Over ItersIters 30500 to 37000[3]
Decreases Over Versions80.3 to 75.1[6]
Has Value83.4[8]
Is PerplexityLanguage Model[8]

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.

isPrimaryEvaluationblah/watt-activation/part-45
ex:sweep
measuresPerformanceblah/watt-activation/part-48
ex:configs
decreasesOverItersblah/watt-activation/part-97
ex:iters-30500-to-37000
measuresModelQualityblah/watt-activation/part-127
ex:language-model
measuresModelQualityblah/watt-activation/part-161
ex:training-session
decreasesOverVersionsblah/watt-activation/part-251
80.3 to 75.1
typeblah/watt-activation/229
ex:Metric
typeblah/watt-activation/244
ex:Metric
hasValueblah/watt-activation/244
83.4
isPerplexityblah/watt-activation/244
ex:language-model

References (8)

8 references
  1. [1]Part 451 fact
    ctx:discord/blah/watt-activation/part-45
  2. [2]Part 481 fact
    ctx:discord/blah/watt-activation/part-48
  3. [3]Part 971 fact
    ctx:discord/blah/watt-activation/part-97
  4. [4]Part 1271 fact
    ctx:discord/blah/watt-activation/part-127
  5. [5]Part 1611 fact
    ctx:discord/blah/watt-activation/part-161
  6. [6]Part 2511 fact
    ctx:discord/blah/watt-activation/part-251
  7. [7]2291 fact
    ctx:discord/blah/watt-activation/229
  8. [8]2443 facts
    ctx:discord/blah/watt-activation/244
    • full textwatt-activation-244
      text/plain3 KBdoc:agent/watt-activation-244/12f61b26-af40-4e33-a8d7-716f2405dc1b
      Show excerpt
      [2026-03-12 05:23] xenonfun: ❯ can we infer on images and audio or get them back out? ⏺ Not yet — the current architecture is encoder-only for image/audio (projects them into the sequence for cross-modal context), but only has a text outpu

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.