Dontopedia

coupling

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

coupling has 52 facts recorded in Dontopedia across 24 references, with 5 live disagreements.

52 facts·39 predicates·24 sources·5 in dispute

Mostly:rdf:type(6), updated by(2), is(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (26)

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.

includesIncludes(4)

representsRepresents(2)

actionKillsAction Kills(1)

alwaysIncreasesAlways Increases(1)

assumedToBeLearnedAssumed to Be Learned(1)

comparesToCompares to(1)

dynamicallyAdjustsDynamically Adjusts(1)

enabledGradientFlowInEnabled Gradient Flow in(1)

hasParameterHas Parameter(1)

hasRicherCouplingHas Richer Coupling(1)

includesSlidersForIncludes Sliders for(1)

isReportingIs Reporting(1)

lacksCouplingLacks Coupling(1)

letsTangentMagnitudeDriveLets Tangent Magnitude Drive(1)

managesCouplingManages Coupling(1)

notVisibleYetInNot Visible Yet in(1)

reducesReduces(1)

resultsInDeltaKappa0.0015Results in Delta Kappa0.0015(1)

successfullyPreventsLearningSuccessfully Prevents Learning(1)

targetTarget(1)

treatsTangentMagnitudeAsTreats Tangent Magnitude As(1)

updatesParameterUpdates Parameter(1)

Other facts (48)

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.

48 facts
PredicateValueRef
Rdf:typeParameter[13]
Rdf:typeMechanism[15]
Rdf:typeParameter[16]
Rdf:typeModel Parameter[20]
Rdf:typeStructural Constant[23]
Rdf:typeParameter[24]
Updated byKuramoto Energy Gradient[2]
Updated byKuramoto Energy Gradient[18]
IsFixed Hyperparameter[3]
IsPer Group K[13]
ControlsPull Strength[5]
ControlsSync Toward[5]
Zero at180°[9]
Zero at[9]
Changes By3e 6 Per StepLohe Optimizer[1]
Driven by Synchronization Physicstrue[2]
Should Be Driven byKuramoto Energy[2]
Not Fighting Synchronizationtrue[2]
NotLearned Parameter[3]
Intentionally Not UpdatedKuramoto Physics Parameters[4]
Is Engine ofSynchronization[5]
Critical Roleengine of synchronization[5]
Negative Evaluationfrozen[5]
Is Frozentrue[5]
Teleological PurposeIncrease to Critical[5]
Set Via CapK C[6]
Has K0.5[7]
Has MajorityInhibitory[8]
Evaluated AsStrong[8]
Has High Absolute Kappa Mean1.3-1.7[8]
Is Essential toTheory[8]
Is Net InhibitoryΚ Mean Negative[8]
Follows Physicsnull[9]
Maximum at90° misalignment[9]
Removed FromParameter Tree[10]
Functions As Multiplier in ForceForce Equation[10]
Is Structural Constantnull[11]
Has Per Layer Groups16[12]
Has Params0.000M[12]
Has Gradient FlowNone[14]
Has StatusExcised From Computation Path[14]
Metaphorical Roleengine of synchronization[15]
Statefrozen[15]
Had Gradient Flowfalse[16]
Changes by0.000003[17]
Update Statusintentionally NOT updated[19]
Self Organizes Through_spectral_lohe_sync[19]
Has PropertySparsity[21]

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.

changesBy3e-6PerStepblah/watt-activation/part-192
ex:lohe-optimizer
updatedByblah/watt-activation/part-193
ex:kuramoto-energy-gradient
drivenBySynchronizationPhysicsblah/watt-activation/part-193
true
shouldBeDrivenByblah/watt-activation/part-193
ex:kuramoto-energy
notFightingSynchronizationblah/watt-activation/part-193
true
isblah/watt-activation/part-194
ex:fixed-hyperparameter
notblah/watt-activation/part-194
ex:learned-parameter
intentionallyNotUpdatedblah/watt-activation/part-196
ex:kuramoto-physics-parameters
isEngineOfblah/watt-activation/part-189
ex:synchronization
controlsblah/watt-activation/part-189
ex:pull-strength
criticalRoleblah/watt-activation/part-189
engine of synchronization
negativeEvaluationblah/watt-activation/part-189
frozen
isFrozenblah/watt-activation/part-189
true
controlsblah/watt-activation/part-189
ex:sync-toward
teleologicalPurposeblah/watt-activation/part-189
ex:increase-to-critical
setViaCapblah/watt-activation/part-206
ex:k-c
hasKblah/watt-activation/part-305
0.5
hasMajorityblah/watt-activation/part-387
ex:inhibitory
evaluatedAsblah/watt-activation/part-387
ex:strong
hasHighAbsoluteKappaMeanblah/watt-activation/part-387
1.3-1.7
isEssentialToblah/watt-activation/part-387
ex:theory
isNetInhibitoryblah/watt-activation/part-387
ex:κ-mean-negative
followsPhysicsblah/watt-activation/part-410
null
zeroAtblah/watt-activation/part-410
180°
maximumAtblah/watt-activation/part-410
90° misalignment
zeroAtblah/watt-activation/part-410
removedFromblah/watt-activation/part-424
ex:parameter-tree
functionsAsMultiplierInForceblah/watt-activation/part-424
ex:force-equation
isStructuralConstantblah/watt-activation/part-437
null
hasPerLayerGroupsblah/watt-activation/part-699
16
hasParamsblah/watt-activation/part-699
0.000M
typeblah/watt-activation/180
ex:Parameter
isblah/watt-activation/180
ex:per-group-k
labelblah/watt-activation/188
coupling
hasGradientFlowblah/watt-activation/188
ex:none
hasStatusblah/watt-activation/188
ex:excised-from-computation-path
typeblah/watt-activation/189
ex:Mechanism
metaphoricalRoleblah/watt-activation/189
engine of synchronization
stateblah/watt-activation/189
frozen
typeblah/watt-activation/190
ex:Parameter
labelblah/watt-activation/190
coupling
hadGradientFlowblah/watt-activation/190
false
changesByblah/watt-activation/192
0.000003
updatedByblah/watt-activation/193
ex:kuramoto-energy-gradient
updateStatusblah/watt-activation/196
intentionally NOT updated
selfOrganizesThroughblah/watt-activation/196
_spectral_lohe_sync
typeblah/watt-activation/198
ex:ModelParameter
hasPropertyblah/watt-activation/207
ex:sparsity
labelblah/watt-activation/212
coupling
labelblah/watt-activation/435
coupling
typeblah/watt-activation/435
ex:structural-constant
typeblah/watt-activation/443
ex:Parameter

References (24)

24 references
  1. [1]Part 1921 fact
    ctx:discord/blah/watt-activation/part-192
  2. [2]Part 1934 facts
    ctx:discord/blah/watt-activation/part-193
  3. [3]Part 1942 facts
    ctx:discord/blah/watt-activation/part-194
  4. [4]Part 1961 fact
    ctx:discord/blah/watt-activation/part-196
  5. [5]Part 1897 facts
    ctx:discord/blah/watt-activation/part-189
  6. [6]Part 2061 fact
    ctx:discord/blah/watt-activation/part-206
  7. [7]Part 3051 fact
    ctx:discord/blah/watt-activation/part-305
  8. [8]Part 3875 facts
    ctx:discord/blah/watt-activation/part-387
  9. [9]Part 4104 facts
    ctx:discord/blah/watt-activation/part-410
  10. [10]Part 4242 facts
    ctx:discord/blah/watt-activation/part-424
  11. [11]Part 4371 fact
    ctx:discord/blah/watt-activation/part-437
  12. [12]Part 6992 facts
    ctx:discord/blah/watt-activation/part-699
  13. [13]1802 facts
    ctx:discord/blah/watt-activation/180
    • full textwatt-activation-180
      text/plain2 KBdoc:agent/watt-activation-180/85d3802b-f63a-40de-acbc-889407c3b80c
      Show excerpt
      [2026-03-10 01:46] lisamegawatts: yes compute it and use that to modulate, i think we probably need to get rid of softmax or ask for a more principled alternative and a config flag. then on the xero harmonics, ask it about using the tempera
  14. [14]1883 facts
    ctx:discord/blah/watt-activation/188
    • full textwatt-activation-188
      text/plain3 KBdoc:agent/watt-activation-188/0b24c5f9-ca6d-47b7-9d97-98b6fac36e0c
      Show excerpt
      [2026-03-10 03:16] xenonfun: well I imagine data from working RotAdamW will be informative for it as to how to correct behavior / step issues in LoheOptimizer [2026-03-10 03:17] xenonfun: also that will be recorded [2026-03-10 03:38] xenonf
  15. [15]1893 facts
    ctx:discord/blah/watt-activation/189
    • full textwatt-activation-189
      text/plain2 KBdoc:agent/watt-activation-189/ee6e7700-8f8f-458c-bd97-cd00204ffe29
      Show excerpt
      [2026-03-10 03:42] xenonfun: ``` What the fix looks like: Coupling κ_g is a scalar per group. Its gradient through the sync step is tractable: at first order, Δcoupling_g ∝ -(∂loss/∂spectra_synced) · (mean_spec_g - spectra_g) — the reado
  16. [16]1903 facts
    ctx:discord/blah/watt-activation/190
    • full textwatt-activation-190
      text/plain3 KBdoc:agent/watt-activation-190/afd2a2d6-55fc-43d9-9655-83cd2755213f
      Show excerpt
      [2026-03-10 03:51] xenonfun: ⏺ The fix is working. Here's the comparison: ``` ┌────────────────┬────────────────┬────────────────────────────┐ │ Metric │ Before fix │ After fix │ ├────────────────┼────────
  17. [17]1921 fact
    ctx:discord/blah/watt-activation/192
    • full textwatt-activation-192
      text/plain3 KBdoc:agent/watt-activation-192/c3ca4e62-2524-47f4-9e3e-6cb28f08f78c
      Show excerpt
      [2026-03-10 04:10] xenonfun: ⏺ Working correctly now. Full comparison: ```┌──────────────────────┬────────────────────┬─────────────────────────┐ │ │ RotAdamW fine-tune │ LoheOptimizer fine-tune │ ├─────────────────
  18. [18]1931 fact
    ctx:discord/blah/watt-activation/193
    • full textwatt-activation-193
      text/plain3 KBdoc:agent/watt-activation-193/b982ee37-c42f-49ed-bcc9-0f5b6259a2c9
      Show excerpt
      [2026-03-10 04:26] lisamegawatts: if its now unfrozen, try the energy loss one [2026-03-10 04:26] xenonfun: ``` Root cause: The loss-gradient-derived coupling update is structurally anti-synchronizing. Coupling should be driven by Kuramoto
  19. [19]1962 facts
    ctx:discord/blah/watt-activation/196
    • full textwatt-activation-196
      text/plain3 KBdoc:agent/watt-activation-196/365c341f-1760-47af-88b6-891859135088
      Show excerpt
      [2026-03-10 05:43] xenonfun: ⏺ Fine-tune works correctly: val ppl 349.9 — matching the documented 349.6 result. The r_kan=0.5 fix is confirmed stable for fine-tuning. [2026-03-10 05:45] xenonfun: Current state: - Committed: 14cd0c6 — KAN
  20. [20]1981 fact
    ctx:discord/blah/watt-activation/198
    • full textwatt-activation-198
      text/plain2 KBdoc:agent/watt-activation-198/ea2dbbd7-7d1c-4ba2-9281-56322a048288
      Show excerpt
      [2026-03-10 06:11] xenonfun: ``` ⏺ --- Summary #1 — features tensor restored One line in lohe_ffn.py. The optimizer already had the branch ready (if 'features' in metrics:). What activates now: - W_out[:, 32..92] (weighted harmon
  21. [21]2071 fact
    ctx:discord/blah/watt-activation/207
    • full textwatt-activation-207
      text/plain3 KBdoc:agent/watt-activation-207/9a40ca53-50d4-413d-9122-939988dbf13e
      Show excerpt
      [2026-03-11 03:15] omega [bot]: Algorithmic approach to hybrid Lohe-Kuramoto model with sparse graph low-rank harmonics: 1. **Model Setup** - Represent each oscillator/unit as a node on a sparse graph. - Each node’s state encodes hig
  22. [22]2121 fact
    ctx:discord/blah/watt-activation/212
    • full textwatt-activation-212
      text/plain3 KBdoc:agent/watt-activation-212/6835fc9f-e8f3-4cfe-b6ab-3f16b5dbc7d2
      Show excerpt
      [2026-03-11 04:12] xenonfun: ``` ⏺ The sidecar data is very revealing! Let me respond to the designer message while the run finishes. --- On Omega's optimizer question: RotationalAdamW is exactly the geometry-aware rotation optimizer d
  23. [23]4352 facts
    ctx:discord/blah/watt-activation/435
    • full textwatt-activation-435
      text/plain2 KBdoc:agent/watt-activation-435/6e80af4f-2aed-449f-9f6a-4750597bfb8e
      Show excerpt
      [2026-03-20 06:59] xenonfun: ``` ⏺ You're right. The PR #7 results (p=0.005, d=2.57, 5/5 seeds) were validated with a specific fusion operator — _block_diagonal_transfer() on vanilla nn.Linear layers. The fusion level (how weights map be
  24. [24]4431 fact
    ctx:discord/blah/watt-activation/443
    • full textwatt-activation-443
      text/plain2 KBdoc:agent/watt-activation-443/9aa84fec-41d2-40a0-a688-c1b81ba3cfd2
      Show excerpt
      [2026-03-20 16:23] omega [bot]: - Phase locking and de-synchronization patterns can represent symbolic states. 5. **Prior Work & Analogies** - Hopfield networks and other attractor neural networks have been shown to simulate finite st

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.