Dontopedia

Current Ar Decoder Attention

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

Current Ar Decoder Attention has 5 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

5 facts·4 predicates·2 sources·1 in dispute

Mostly:uses(2), uses block(1), violates principles(1)

Maturity scale raw canonical shape-checked rule-derived certified

Other facts (5)

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.

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.

usesBlockblah/watt-activation/part-302
ex:standard-transformer-block
violatesPrinciplesblah/watt-activation/part-302
ex:architecture-design-principles
usesblah/watt-activation/300
ex:standard-transformer-block
usesblah/watt-activation/300
softmax
violatesblah/watt-activation/300
ex:architecture-design-principles

References (2)

2 references
  1. [1]Part 3022 facts
    ctx:discord/blah/watt-activation/part-302
  2. [2]3003 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.