Dontopedia

adjacency

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

adjacency has 26 facts recorded in Dontopedia across 9 references, with 4 live disagreements.

26 facts·17 predicates·9 sources·4 in dispute

Mostly:rdf:type(4), is structural constant(3), zeroed out by(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (2)

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.

involvesRemovingInvolves Removing(1)

neverBenefitedFromNever Benefited From(1)

Other facts (23)

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.

23 facts
PredicateValueRef
Rdf:typeModel Parameter[6]
Rdf:typeParameter[7]
Rdf:typeStructural Constant[8]
Rdf:typeStructural Constant[9]
Is Structural ConstantTrue[3]
Is Structural Constantnull[4]
Is Structural Constanttrue[8]
Zeroed Out byRotational Adamw[2]
Zeroed Out byRotational Adam W[6]
Used inEinsum Gj Btjh Btgh[1]
Has Negative Allowednull[1]
Has Essential Role inSync Coherence[2]
Zeroed Itself Outtrue[2]
Is Irrelevant toNan Issue[2]
Not UpdatedTrue[3]
Not CoincidentalTrue[5]
Row Norm Decay0.354 to ~2e-9[6]
Decay Duration10K steps[6]
Self Zeroedtrue[6]
Model Never Benefited Fromtrue[6]
Irrelevant to Na Ntrue[6]
Had Gradient Flowfalse[7]
Is Not Updatedtrue[8]

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.

usedInblah/watt-activation/part-136
ex:einsum-gj-btjh-btgh
hasNegativeAllowedblah/watt-activation/part-136
null
zeroedOutByblah/watt-activation/part-138
ex:rotational-adamw
hasEssentialRoleInblah/watt-activation/part-138
ex:sync-coherence
zeroedItselfOutblah/watt-activation/part-138
true
isIrrelevantToblah/watt-activation/part-138
ex:nan-issue
notUpdatedblah/watt-activation/part-210
ex:true
isStructuralConstantblah/watt-activation/part-210
ex:true
isStructuralConstantblah/watt-activation/part-437
null
notCoincidentaleky-rosie-kitty/kinship-part1
ex:true
labelblah/watt-activation/138
adjacency
typeblah/watt-activation/138
ex:ModelParameter
zeroedOutByblah/watt-activation/138
ex:RotationalAdamW
rowNormDecayblah/watt-activation/138
0.354 to ~2e-9
decayDurationblah/watt-activation/138
10K steps
selfZeroedblah/watt-activation/138
true
modelNeverBenefitedFromblah/watt-activation/138
true
irrelevantToNaNblah/watt-activation/138
true
typeblah/watt-activation/190
ex:Parameter
labelblah/watt-activation/190
adjacency
hadGradientFlowblah/watt-activation/190
false
typeblah/watt-activation/209
ex:StructuralConstant
isStructuralConstantblah/watt-activation/209
true
isNotUpdatedblah/watt-activation/209
true
labelblah/watt-activation/435
adjacency
typeblah/watt-activation/435
ex:structural-constant

References (9)

9 references
  1. [1]Part 1362 facts
    ctx:discord/blah/watt-activation/part-136
  2. [2]Part 1384 facts
    ctx:discord/blah/watt-activation/part-138
  3. [3]Part 2102 facts
    ctx:discord/blah/watt-activation/part-210
  4. [4]Part 4371 fact
    ctx:discord/blah/watt-activation/part-437
  5. [5]Kinship Part11 fact
    ctx:genes/eky-rosie-kitty/kinship-part1
  6. [6]1388 facts
    ctx:discord/blah/watt-activation/138
    • full textwatt-activation-138
      text/plain3 KBdoc:agent/watt-activation-138/9bd08756-4bea-4055-bcfd-5d3ed62434a1
      Show excerpt
      [2026-03-09 06:23] xenonfun: ``` ⏺ No — softmax is on self.log_adjacency which is a static (G, G) parameter tensor, completely independent of T. It runs once per forward pass in O(G²) = O(64). The sequence-length work is entirely in _gate
  7. [7]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 │ ├────────────────┼────────
  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]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

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.