Dontopedia

manifold

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

manifold has 13 facts recorded in Dontopedia across 9 references, with 2 live disagreements.

13 facts·7 predicates·9 sources·2 in dispute

Mostly:rdf:type(3), underlies dynamics(1), native for(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (22)

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.

staysOnStays on(3)

notDerivedFromNot Derived From(2)

attributedLearningToAttributed Learning to(1)

carriedPassengerCarried Passenger(1)

enablesMoreEfficientSearchEnables More Efficient Search(1)

freesEmbedWeightFrees Embed Weight(1)

freesLmHeadWeightFrees Lm Head Weight(1)

illegitimatePurposesIllegitimate Purposes(1)

includesIncludes(1)

isIs(1)

isProvablyOnIs Provably on(1)

keptNearKept Near(1)

lacksConstraintLacks Constraint(1)

locatedAtLocated at(1)

locatedOnLocated on(1)

locationLocation(1)

preservesPreserves(1)

shouldStayOnShould Stay on(1)

workedOnManuallyWorked on Manually(1)

Other facts (9)

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.

9 facts
PredicateValueRef
Rdf:typeMathematical Object[6]
Rdf:typeMathematical Structure[7]
Rdf:typeModel Component[9]
Underlies DynamicsLohe Dynamics[1]
Native forPhases[2]
Is Correct for DC Neutral Filterstrue[3]
Is Repeatedly EmphasizedGet Back on Manifold[4]
Has Params0.027M[5]
Has Per Layer Groups16[5]

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.

underliesDynamicsblah/watt-activation/part-137
ex:lohe-dynamics
nativeForblah/watt-activation/part-321
ex:phases
isCorrectForDcNeutralFiltersblah/watt-activation/part-352
true
isRepeatedlyEmphasizedblah/watt-activation/part-692
ex:get-back-on-manifold
hasParamsblah/watt-activation/part-699
0.027M
hasPerLayerGroupsblah/watt-activation/part-699
16
typeblah/watt-activation/137
ex:MathematicalObject
labelblah/watt-activation/137
manifold
typeblah/watt-activation/343
ex:MathematicalStructure
labelblah/watt-activation/343
manifold
labelblah/watt-activation/345
the manifold
typeblah/watt-activation/620
ex:ModelComponent
labelblah/watt-activation/620
the manifold

References (9)

9 references
  1. [1]Part 1371 fact
    ctx:discord/blah/watt-activation/part-137
  2. [2]Part 3211 fact
    ctx:discord/blah/watt-activation/part-321
  3. [3]Part 3521 fact
    ctx:discord/blah/watt-activation/part-352
  4. [4]Part 6921 fact
    ctx:discord/blah/watt-activation/part-692
  5. [5]Part 6992 facts
    ctx:discord/blah/watt-activation/part-699
  6. [6]1372 facts
    ctx:discord/blah/watt-activation/137
    • full textwatt-activation-137
      text/plain2 KBdoc:agent/watt-activation-137/9608fbdb-8ce7-4e5b-ac20-5c329d46eade
      Show excerpt
      [2026-03-09 06:07] xenonfun: ``` ❯ are you sure this is principaled? ⏺ No, you're right to push back. L1 normalization is ad-hoc — it bounds the magnitude but it's not derived from the manifold. The principled fix is to normalize the mean
  7. [7]3432 facts
    ctx:discord/blah/watt-activation/343
    • full textwatt-activation-343
      text/plain2 KBdoc:agent/watt-activation-343/758b6afd-7936-40ff-806a-3684984cdf9e
      Show excerpt
      [2026-03-15 23:13] xenonfun: ``` ⏺ Pushed f5d17e5. All EMA/stability/spike hacks removed. Both adaptive LR modes are now pure physics: direct measurement × capacity theory × convergence decay. On the LoheCrossCoupleModes comment — that's
  8. [8]3451 fact
    ctx:discord/blah/watt-activation/345
    • full textwatt-activation-345
      text/plain3 KBdoc:agent/watt-activation-345/c59946eb-7ad9-465b-939c-f70436033800
      Show excerpt
      [2026-03-16 01:39] xenonfun: ⏺ Yes — principled noise injection is exactly what communications systems do. Three reasons it could help: 1. Stochastic resonance. In nonlinear systems (which Lohe sync IS), a small amount of noise can actua
  9. [9]6202 facts
    ctx:discord/blah/watt-activation/620
    • full textwatt-activation-620
      text/plain2 KBdoc:agent/watt-activation-620/76566bac-aa9d-4345-b1ab-afded7e71af5
      Show excerpt
      [2026-04-11 10:36] lisamegawatts: The loss dropped from ~36 to 9.3 in 100 steps — the manifold is learning! The output went from random multilingual tokens to English words with approximate semantic relevance ("technology", "processing", "e

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.