Dontopedia

Ternary Constraint

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

Ternary Constraint has 4 facts recorded in Dontopedia across 3 references.

4 facts·4 predicates·3 sources

Mostly:acts as implicit regularization(1), acts as(1), rdf:type(1)

Maturity scale raw canonical shape-checked rule-derived certified

Other facts (4)

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.

4 facts
PredicateValueRef
Acts As Implicit RegularizationFfn Layers[1]
Acts AsImplicit Regularization[2]
Rdf:typeConstraint[3]
Constrains Direction to Discrete Settrue[3]

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.

4 undated
—
actsAsImplicitRegularizationblah/watt-activation/part-279
ex:ffn-layers
—
actsAsblah/watt-activation/277
ex:implicit-regularization
—
typeblah/watt-activation/275
ex:Constraint
—
constrainsDirectionToDiscreteSetblah/watt-activation/275
true

References (3)

3 references
  1. [1]Part 2791 fact
    ctx:discord/blah/watt-activation/part-279
  2. [2]2771 fact
    ctx:discord/blah/watt-activation/277
    • full textwatt-activation-277
      text/plain2 KBdoc:agent/watt-activation-277/678013e8-df75-4d10-9db8-f270e925c768
      Show excerpt
      [2026-03-13 22:08] xenonfun: ``` ✻ Implementing SphericalCodebook… (10m 18s · ↓ 15.3k tokens) ⎿  ◼ Implement SphericalCodebook ◻ Implement SphericalVQBottleneck ◻ Implement SphericalVQHead + _logit helper ◻ Write tests for …
  3. [3]2752 facts
    ctx:discord/blah/watt-activation/275
    • full textwatt-activation-275
      text/plain3 KBdoc:agent/watt-activation-275/149bf24b-54fb-4412-b289-e2e03bccffe2
      Show excerpt
      [2026-03-13 20:46] xenonfun: ⏺ This tells a clear story: Current trained weights are NOT naturally ternary. Only ~46% of values are near {-1, 0, 1} after scaling (random Gaussian would give ~47%, so no better than chance). Relative err…

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.

↑