Dontopedia

Lohe Ar Decoder

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

Lohe Ar Decoder has 14 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

14 facts·12 predicates·2 sources·1 in dispute

Mostly:has parameter(3), commits to spherical geometry(1), deployed in(1)

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.

announcesPushAnnounces Push(1)

isIs(1)

outputsToOutputs to(1)

precedesStagePrecedes Stage(1)

Other facts (14)

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.

14 facts
PredicateValueRef
Has Parameterd=384[2]
Has Parameter3-layers[2]
Has Parameter15k-steps[2]
Commits to Spherical GeometryS D 1[1]
Deployed inRjs Lohedec[1]
Has Dimension384[1]
Has Num Layers3[1]
Precedes StageBytes[1]
ProducesVmf Byte Logits[1]
Running in BranchRjs Lohedec[1]
Trained for Steps15000[1]
Has Statusrunning[2]
Has Output TypeVmf Byte Logits[2]
Outputs tobytes[2]

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.

commitsToSphericalGeometryblah/watt-activation/part-302
ex:s-d-1
deployedInblah/watt-activation/part-302
ex:rjs-lohedec
hasDimensionblah/watt-activation/part-302
384
hasNumLayersblah/watt-activation/part-302
3
precedesStageblah/watt-activation/part-302
ex:bytes
producesblah/watt-activation/part-302
ex:vmf-byte-logits
runningInBranchblah/watt-activation/part-302
ex:rjs-lohedec
trainedForStepsblah/watt-activation/part-302
15000
hasParameterblah/watt-activation/300
d=384
hasParameterblah/watt-activation/300
3-layers
hasParameterblah/watt-activation/300
15k-steps
hasStatusblah/watt-activation/300
running
hasOutputTypeblah/watt-activation/300
ex:vmf-byte-logits
outputsToblah/watt-activation/300
bytes

References (2)

2 references
  1. [1]Part 3028 facts
    ctx:discord/blah/watt-activation/part-302
  2. [2]3006 facts
    ctx:discord/blah/watt-activation/300
    • full textwatt-activation-300
      text/plain3 KBdoc:agent/watt-activation-300/3b6edccf-3524-4608-838f-25890efaea15
      Show excerpt
      [2026-03-14 06:34] xenonfun: ``` 3. Manual attention (lines 110-128) — Hand-rolled softmax attention instead of using mx.fast.scaled_dot_product_attention. MLX's fused attention kernel is significantly faster for small sequence lengths.

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.