Dontopedia

meaningful comparison

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

meaningful comparison has 8 facts recorded in Dontopedia across 1 reference, with 1 live disagreement.

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

Mostly:involves entity(2), rdf:type(1), involves action(1)

Maturity scale raw canonical shape-checked rule-derived certified

Other facts (7)

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.

7 facts
PredicateValueRef
Involves EntityGpt 2 Small[1]
Involves EntityAnchorkan[1]
Rdf:typeProposed Method[1]
Involves ActionTrain Both Architectures[1]
Constraint on Datasame data[1]
Constraint on Tokenssame number of tokens[1]
Measures OutcomeTest Ppl[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.

typeblah/watt-activation/92
ex:ProposedMethod
involvesActionblah/watt-activation/92
ex:train-both-architectures
labelblah/watt-activation/92
meaningful comparison
involvesEntityblah/watt-activation/92
ex:gpt-2-small
involvesEntityblah/watt-activation/92
ex:anchorkan
constraintOnDatablah/watt-activation/92
same data
constraintOnTokensblah/watt-activation/92
same number of tokens
measuresOutcomeblah/watt-activation/92
ex:test-ppl

References (1)

1 references
  1. [1]928 facts
    ctx:discord/blah/watt-activation/92
    • full textwatt-activation-92
      text/plain3 KBdoc:agent/watt-activation-92/a597b55a-3d12-478b-951d-f09c655a8870
      Show excerpt
      [2026-03-08 01:46] xenonfun: ``` Direct comparison is tricky but here are the reference points: GPT-2 Small (124M) published benchmarks: - WikiText-103 test: 29.4 PPL - Penn Treebank: 65.9 PPL - Trained on ~8-9B tokens of WebText

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.