Dontopedia

Lohe S³

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

Lohe S³ has 45 facts recorded in Dontopedia across 13 references, with 5 live disagreements.

45 facts·35 predicates·13 sources·5 in dispute

Mostly:rdf:type(4), is type of(2), generalizes(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (23)

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.

isExampleOfIs Example of(2)

assertsKnowledgeOfAsserts Knowledge of(1)

connectsToConnects to(1)

destinationModelDestination Model(1)

discussesTopicDiscusses Topic(1)

establishesConnectionEstablishes Connection(1)

generalizedByGeneralized by(1)

hasBpbImprovementOverHas Bpb Improvement Over(1)

hasHigherParamCountThanHas Higher Param Count Than(1)

hasLowerBpbValueThanHas Lower Bpb Value Than(1)

hasSequenceHas Sequence(1)

implementsOscillatorModelImplements Oscillator Model(1)

isDestructiveIs Destructive(1)

isEspeciallyInterestingForIs Especially Interesting for(1)

methodMethod(1)

outperformsOnBpbOutperforms on Bpb(1)

preservedThroughPreserved Through(1)

presupposesExistenceOfPresupposes Existence of(1)

proposedUpgradeToProposed Upgrade to(1)

referencesReferences(1)

referencesPaperReferences Paper(1)

toTo(1)

Other facts (41)

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.

41 facts
PredicateValueRef
Rdf:typeMathematical Model[9]
Rdf:typeModel[10]
Rdf:typeModel[12]
Rdf:typeModel Architecture[13]
Is Type ofMatrix Model[3]
Is Type ofSpherical Model[3]
GeneralizesKuramoto Model[9]
GeneralizesSynchronization[12]
InvolvesQuadratic Interactions[12]
InvolvesMatrix Operations[12]
Presupposes High Dimensional Couplingnull[1]
Defined on ManifoldS^n U(d)[1]
Evaluated Positively Asricher phase structure[1]
Extends From DimensionS¹[1]
Extends to DimensionS^n[1]
Sourced FromArxiv 2109 14761[1]
Generalizes ModelKuramoto Model[1]
Involves Group U(d)null[1]
Originates From PaperArxiv 2109 14761[1]
Extended toLohe Hermitian Sphere Model[2]
Generalizes to Lhsnull[2]
Captures Rich DynamicsHigh Dimensional[3]
Has Num Layers6[4]
Has Attention Projections Per Layer4[4]
Has Ffn Projections Per Layer2[4]
Has Total Weight Matrices36[4]
Referenced inContext[5]
Known Model ofSynchronization[6]
Relates toSchrodinger[7]
Has Bpb3.278[8]
Has Params341730[8]
Has It Per S14.9[8]
Has Higher It Per S Value ThanLinear Kan Model[8]
Generalizes FromS1 Space[9]
Generalizes toUnitary Group Space[9]
Variant ofLohe S⁷[10]
Has ExtensionLohe Hermitian Sphere Model[11]
Applies toHigher Dimensional Quantum Like Oscillators[12]
Has FeatureRicher Coupling[12]
IsComputationally Demanding[12]
Has Right Structuretrue[13]

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.

45 undated
—
presupposesHighDimensionalCouplingblah/watt-activation/part-67
null
—
definedOnManifoldblah/watt-activation/part-67
ex:s^n-u(d)
—
evaluatedPositivelyAsblah/watt-activation/part-67
richer phase structure
—
extendsFromDimensionblah/watt-activation/part-67
ex:s¹
—
extendsToDimensionblah/watt-activation/part-67
ex:s^n
—
sourcedFromblah/watt-activation/part-67
ex:arxiv-2109-14761
—
generalizesModelblah/watt-activation/part-67
ex:kuramoto-model
—
involvesGroupU(d)blah/watt-activation/part-67
null
—
originatesFromPaperblah/watt-activation/part-67
ex:arxiv-2109-14761
—
extendedToblah/watt-activation/part-185
ex:lohe-hermitian-sphere-model
—
generalizesToLhsblah/watt-activation/part-185
null
—
capturesRichDynamicsblah/watt-activation/part-208
ex:high-dimensional
—
isTypeOfblah/watt-activation/part-208
ex:matrix-model
—
isTypeOfblah/watt-activation/part-208
ex:spherical-model
—
hasNumLayersblah/watt-activation/part-277
6
—
hasAttentionProjectionsPerLayerblah/watt-activation/part-277
4
—
hasFfnProjectionsPerLayerblah/watt-activation/part-277
2
—
hasTotalWeightMatricesblah/watt-activation/part-277
36
—
referencedInblah/watt-activation/part-410
ex:context
—
knownModelOfblah/watt-activation/part-564
ex:synchronization
—
relatesToblah/watt-activation/part-572
ex:schrodinger
—
hasBpbblah/watt-activation/part-643
3.278
—
hasParamsblah/watt-activation/part-643
341730
—
hasItPerSblah/watt-activation/part-643
14.9
—
hasHigherItPerSValueThanblah/watt-activation/part-643
ex:linear-kan-model
—
typeblah/watt-activation/67
ex:MathematicalModel
—
labelblah/watt-activation/67
Lohe model
—
generalizesblah/watt-activation/67
ex:kuramoto-model
—
generalizesFromblah/watt-activation/67
ex:s1-space
—
generalizesToblah/watt-activation/67
ex:unitary-group-space
—
typeblah/watt-activation/69
ex:Model
—
labelblah/watt-activation/69
Lohe S³
—
variantOfblah/watt-activation/69
Lohe S⁷
—
hasExtensionblah/watt-activation/185
ex:lohe-hermitian-sphere-model
—
typeblah/watt-activation/206
ex:Model
—
labelblah/watt-activation/206
Lohe models
—
generalizesblah/watt-activation/206
ex:synchronization
—
appliesToblah/watt-activation/206
ex:higher-dimensional-quantum-like-oscillators
—
hasFeatureblah/watt-activation/206
ex:richer-coupling
—
isblah/watt-activation/206
ex:computationally-demanding
—
involvesblah/watt-activation/206
ex:quadratic-interactions
—
involvesblah/watt-activation/206
ex:matrix-operations
—
typeblah/watt-activation/275
ex:ModelArchitecture
—
labelblah/watt-activation/275
Lohe models
—
hasRightStructureblah/watt-activation/275
true

References (13)

13 references
  1. [1]Part 679 facts
    ctx:discord/blah/watt-activation/part-67
  2. [2]Part 1852 facts
    ctx:discord/blah/watt-activation/part-185
  3. [3]Part 2083 facts
    ctx:discord/blah/watt-activation/part-208
  4. [4]Part 2774 facts
    ctx:discord/blah/watt-activation/part-277
  5. [5]Part 4101 fact
    ctx:discord/blah/watt-activation/part-410
  6. [6]Part 5641 fact
    ctx:discord/blah/watt-activation/part-564
  7. [7]Part 5721 fact
    ctx:discord/blah/watt-activation/part-572
  8. [8]Part 6434 facts
    ctx:discord/blah/watt-activation/part-643
  9. [9]675 facts
    ctx:discord/blah/watt-activation/67
    • full textwatt-activation-67
      text/plain2 KBdoc:agent/watt-activation-67/7efba5f2-4ec4-453b-9d73-df8423b87905
      Show excerpt
      [2026-03-07 16:00] xenonfun: --- Now, on the Lohe model — from the paper (arXiv 2109.14761): The Lohe model generalizes Kuramoto from S¹ (unit circle, scalar angles) to S^n / U(d) (unitary matrices). The dynamics become: U̇ᵢUᵢ† = iH…
  10. [10]693 facts
    ctx:discord/blah/watt-activation/69
    • full textwatt-activation-69
      text/plain2 KBdoc:agent/watt-activation-69/115feb57-96b9-47df-9acf-f435eab39352
      Show excerpt
      [2026-03-07 16:49] xenonfun: ``` [E_mhkan_h5] iter 10000/10000 | avg_loss=4.5126 | PPL=91.2 | r=0.000 | E=0.000 | clusters=0 | 134 it/s (68.6K tok/s) [E2_mhkan_h4] iter 2000/10000 | avg_loss=5.4540 | PPL…
  11. [11]1851 fact
    ctx:discord/blah/watt-activation/185
    • full textwatt-activation-185
      text/plain3 KBdoc:agent/watt-activation-185/fcee3d0e-68fc-4f0b-ad9d-157115bfbade
      Show excerpt
      [2026-03-10 02:38] lisamegawatts: i think this part is wrong, it should not init at zero they need frequencies. i also don't think it needs gelu, the linear error is inherently in the sphere; The Lohe sphere model, a generalization of the K…
  12. [12]2068 facts
    ctx:discord/blah/watt-activation/206
    • full textwatt-activation-206
      text/plain2 KBdoc:agent/watt-activation-206/f5849082-cbd0-4eef-b2ec-fa71f040c9a9
      Show excerpt
      [2026-03-11 03:13] omega [bot]: Blending Lohe and Kuramoto methods to achieve linear-time computation is an intriguing idea—both operate on synchronization dynamics but differ in complexity and expressive power. Kuramoto's model is a class…
  13. [13]2753 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.

↑