Dontopedia

einsum

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

einsum has 4 facts recorded in Dontopedia across 3 references, with 1 live disagreement.

4 facts·2 predicates·3 sources·1 in dispute
Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (1)

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.

maintainsUsageOfMaintains Usage of(1)

Other facts (2)

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.

2 facts
PredicateValueRef
Rdf:typeCode Operation[2]
Computational ComplexityO(G²·H·B·T)[3]

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.

labelblah/watt-activation/78
einsum
typeblah/watt-activation/136
ex:CodeOperation
labelblah/watt-activation/138
einsum 'gj,btjh->btgh'
computationalComplexityblah/watt-activation/138
O(G²·H·B·T)

References (3)

3 references
  1. [1]781 fact
    ctx:discord/blah/watt-activation/78
    • full textwatt-activation-78
      text/plain2 KBdoc:agent/watt-activation-78/29aa0ca9-9bd7-4e6c-a0f9-62769e7f15b8
      Show excerpt
      [2026-03-07 19:03] xenonfun: ``` 25/25 still passing. Re your points: - 7.1: Added mx.contiguous() before folding in __call__. No need in step() since the squeeze already collapses the length-1 dim, producing contiguous output. - 7.2
  2. [2]1361 fact
    ctx:discord/blah/watt-activation/136
    • full textwatt-activation-136
      text/plain2 KBdoc:agent/watt-activation-136/b63e2d8b-e5e6-437a-bc06-afc61927522e
      Show excerpt
      [2026-03-09 06:01] xenonfun: okay we got issue: ``` step 10300/16670 61.8% loss=6.1309 ppl= 459.8 lr=4.03e-05 642ms 12,764tok/s eta=68min step 10400/16670 62.4% loss=nan ppl= nan lr=3.95e-05 644ms 12,714tok/s eta=67min s
  3. [3]1382 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

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.