Dontopedia

coupling K

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

coupling K has 44 facts recorded in Dontopedia across 14 references, with 6 live disagreements.

44 facts·30 predicates·14 sources·6 in dispute

Mostly:rdf:type(6), is structural(3), is structural constant(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (4)

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.

causeDivergenceCause Divergence(1)

describesMetricDescribes Metric(1)

hasMemberHas Member(1)

mentionsMentions(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:typeStructural Constant[8]
Rdf:typeMetric[10]
Rdf:typeVisualization Panel[11]
Rdf:typeVisualization[12]
Rdf:typeVisualization[13]
Rdf:typeHyperparameter[14]
Is StructuralTrue[6]
Is Structuraltrue[9]
Is Structuraltrue[11]
Is Structural ConstantTrue[2]
Is Structural Constanttrue[8]
Has Value0.176[9]
Has Value0.177[14]
Is Learnedfalse[9]
Is Learnedfalse[11]
Approximate Value0.17[10]
Approximate Value0.18[10]
Differs FromGate G[1]
Computed ViaCoupling Computer[1]
ShapesDynamics[1]
Askswho should influence whom's phase?[1]
Not UpdatedTrue[2]
Locks to Value~0.176[3]
Confirms FixAnti Pattern[3]
Barely MovesTrue[3]
Is Structural Not LearnedTrue[3]
Is Middle Right Paneltrue[4]
Values Diverge Faster Than Beforetrue[4]
Is Stable Across Blocks~0.16-0.18[5]
Shows No Runawaytrue[5]
Matches ExpectationTrue[6]
Is Not LearnedTrue[6]
Computed byCoupling Computer[7]
FunctionShapes Dynamics[7]
QueryInfluence Question[7]
Is Not Updatedtrue[8]
Applies toAll Blocks[9]
Has VolatilityLow[9]
Location in Layoutmiddle-right[12]
Shows Featureclear-divergence[12]
Has LocationMiddle Right Position[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.

differsFromblah/watt-activation/part-65
ex:gate-g
computedViablah/watt-activation/part-65
ex:coupling-computer
shapesblah/watt-activation/part-65
ex:dynamics
asksblah/watt-activation/part-65
who should influence whom's phase?
isStructuralConstantblah/watt-activation/part-210
ex:true
notUpdatedblah/watt-activation/part-210
ex:true
locksToValueblah/watt-activation/part-233
~0.176
confirmsFixblah/watt-activation/part-233
ex:anti-pattern
barelyMovesblah/watt-activation/part-233
ex:true
isStructuralNotLearnedblah/watt-activation/part-233
ex:true
isMiddleRightPanelblah/watt-activation/part-250
true
valuesDivergeFasterThanBeforeblah/watt-activation/part-250
true
isStableAcrossBlocksblah/watt-activation/part-251
~0.16-0.18
showsNoRunawayblah/watt-activation/part-251
true
matchesExpectationblah/watt-activation/part-247
ex:true
isNotLearnedblah/watt-activation/part-247
ex:true
isStructuralblah/watt-activation/part-247
ex:true
computedByblah/watt-activation/65
ex:coupling-computer
functionblah/watt-activation/65
ex:shapes-dynamics
queryblah/watt-activation/65
ex:influence-question
typeblah/watt-activation/209
ex:StructuralConstant
isStructuralConstantblah/watt-activation/209
true
isNotUpdatedblah/watt-activation/209
true
hasValueblah/watt-activation/232
0.176
appliesToblah/watt-activation/232
ex:all-blocks
hasVolatilityblah/watt-activation/232
ex:low
isStructuralblah/watt-activation/232
true
isLearnedblah/watt-activation/232
false
typeblah/watt-activation/235
ex:Metric
labelblah/watt-activation/235
coupling K
approximateValueblah/watt-activation/235
0.17
approximateValueblah/watt-activation/235
0.18
typeblah/watt-activation/246
ex:VisualizationPanel
labelblah/watt-activation/246
Middle-right (Coupling K)
isStructuralblah/watt-activation/246
true
isLearnedblah/watt-activation/246
false
typeblah/watt-activation/248
ex:Visualization
locationInLayoutblah/watt-activation/248
middle-right
showsFeatureblah/watt-activation/248
clear-divergence
typeblah/watt-activation/249
ex:Visualization
labelblah/watt-activation/249
Coupling K (middle-right)
hasLocationblah/watt-activation/249
ex:middle-right-position
typeblah/watt-activation/351
ex:Hyperparameter
hasValueblah/watt-activation/351
0.177

References (14)

14 references
  1. [1]Part 654 facts
    ctx:discord/blah/watt-activation/part-65
  2. [2]Part 2102 facts
    ctx:discord/blah/watt-activation/part-210
  3. [3]Part 2334 facts
    ctx:discord/blah/watt-activation/part-233
  4. [4]Part 2502 facts
    ctx:discord/blah/watt-activation/part-250
  5. [5]Part 2512 facts
    ctx:discord/blah/watt-activation/part-251
  6. [6]Part 2473 facts
    ctx:discord/blah/watt-activation/part-247
  7. [7]653 facts
    ctx:discord/blah/watt-activation/65
    • full textwatt-activation-65
      text/plain3 KBdoc:agent/watt-activation-65/3eb67599-95d0-41e7-8dbb-3ef5adce2574
      Show excerpt
      [2026-03-07 15:47] xenonfun: ``` What the simplification would lose The "near-zero-cost drop-in" claim is mostly right for a single-layer, single-step model. But there are structural features the Kuramoto architecture provides that a n
  8. [8]2093 facts
    ctx:discord/blah/watt-activation/209
    • full textwatt-activation-209
      text/plain2 KBdoc:agent/watt-activation-209/d7eabcf9-d506-432f-9a2c-b25cf5ef8ccd
      Show excerpt
      [2026-03-11 03:51] xenonfun: ```# coupling (K) and adjacency are structural constants — not updated. 598 + # v2: update harmonic_coeffs (G×H learned frequency weights) 599 + # v3: update mode_amplitudes (k scalars,
  9. [9]2325 facts
    ctx:discord/blah/watt-activation/232
    • full textwatt-activation-232
      text/plain3 KBdoc:agent/watt-activation-232/3c01e7f2-4764-4305-aaa5-72adde3c0ccb
      Show excerpt
      [2026-03-11 20:31] xenonfun: ## SpectralAttention vs. AnchorKAN (files: Screenshot_2026-03-11_at_4.31.27_PM.png) [2026-03-11 20:39] xenonfun: ``` ⏺ Here's what each panel is showing, with the interesting bits: --- Row 1 — Loss + Global
  10. [10]2354 facts
    ctx:discord/blah/watt-activation/235
    • full textwatt-activation-235
      text/plain2 KBdoc:agent/watt-activation-235/2b477fba-6b21-4139-a3e7-6c48c5dad99f
      Show excerpt
      [2026-03-11 22:42] xenonfun: ⏺ Done. Pushed 34b7246. Summary of what landed: - Results: anchor_kan best ppl 155.6 / 52K tok/s, spectral 116.4 / 43.7K tok/s - parallel prefill: 120× faster for spectral, auto-fallback for anchor_kan -
  11. [11]2464 facts
    ctx:discord/blah/watt-activation/246
    • full textwatt-activation-246
      text/plain3 KBdoc:agent/watt-activation-246/e98a7e00-4e3f-4e35-bccb-faff629fa820
      Show excerpt
      [2026-03-12 07:06] xenonfun: ```[03:04:05] step 2000/12432 16.1% txt=4.411(82ppl) img=0.000 aud=2.025 r=0.375 lr=4.79e-05 150ms 69,028tok/s [T:1000 I:0 A:1000] eta=26min VAL step 2000 loss=4.4035 ppl=81.7 * best [03:04:29]
  12. [12]2483 facts
    ctx:discord/blah/watt-activation/248
    • full textwatt-activation-248
      text/plain2 KBdoc:agent/watt-activation-248/aaa8be70-5afb-4a65-b9f4-713720917264
      Show excerpt
      [2026-03-12 08:11] xenonfun: ⏺ That's v3 epoch 1 (the full COCO+audio+text run). Notable evolution compared to earlier: r heatmap (top-left): Same block stratification — B0-B1 hot (r~0.5), B4-B5 cool (r~0.37). Stable throughout, no phase
  13. [13]2493 facts
    ctx:discord/blah/watt-activation/249
    • full textwatt-activation-249
      text/plain2 KBdoc:agent/watt-activation-249/8436e2be-67b0-44b5-9c54-97c19c68045d
      Show excerpt
      [2026-03-12 08:24] xenonfun: ⏺ Early packed phase data — only ~550 steps in but already showing interesting dynamics: r heatmap (top-left): Much more visible step-to-step fluctuation than the unpacked runs. The vertical striping pattern
  14. [14]3512 facts
    ctx:discord/blah/watt-activation/351
    • full textwatt-activation-351
      text/plain3 KBdoc:agent/watt-activation-351/a1067b53-0e70-4497-b6fc-75de08ee45fa
      Show excerpt
      [2026-03-16 22:01] xenonfun: still working on unshackling our dynamics from locking in, now that we removed most of the shackles claude put on it with non-manifold preserving operations for most of it. finally getting some movement, tho thi

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.