Dontopedia
Explore

Model Output Observation 8k

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-07-01.)

Model Output Observation 8k has 15 facts recorded in Dontopedia across 1 reference.

15 facts·15 predicates·1 sources

Mostly:quality descriptor cleaned(1), possibly explained by(1), quality qualifier normalized(1)

Maturity scale raw canonical shape-checked rule-derived certified

Quality Descriptor CleanedqualityDescriptorCleaned

  • significantly[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5

Possibly Explained bypossiblyExplainedBy

Quality Qualifier NormalizedqualityQualifierNormalized

  • significantly[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5

Contrasts WithcontrastsWith

Used Vocab SizeusedVocabSize

Is Observation ofisObservationOf

  • Model[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5

Beforebefore

Quality QualifierqualityQualifier

  • signifigantly[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5

Result QualityresultQuality

  • worse[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5

Under Training ConditionunderTrainingCondition

At Vocab SizeatVocabSize

Performed byperformedBy

  • Model[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5

Inbound mentions (6)

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.

afterAfter(1)

appliesToObservationApplies to Observation(1)

contrastsWithContrasts With(1)

hasObservationHas Observation(1)

referencedInObservationReferenced in Observation(1)

relevanceToObservationRelevance to Observation(1)

Other facts (3)

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.

3 facts
PredicateValueRef
Rdfs:label8K vocab is signifigantly worse output[1]
Attested bySource Utterance[1]
Rdf:typeObservation Event[1]

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.

attestedBydocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:source-utterance
atVocabSizedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:vocab-size-8k
beforedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:model-attention-observation-100k
contrastsWithdocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:model-attention-observation-100k
isObservationOfdocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:model
performedBydocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:model
possiblyExplainedBydocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:model-lopsidedness-assertion
qualityDescriptorCleaneddocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
significantly
qualityQualifierdocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
signifigantly
qualityQualifierNormalizeddocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
significantly
labeldocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
8K vocab is signifigantly worse output
typedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:observation-event
resultQualitydocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
worse
underTrainingConditiondocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:training-context-same
usedVocabSizedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:vocab-size-8k

References (1)

1 references
  1. customctx:claims/document/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
    • full textxenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K voc
      text/plain680 Bdiscord:msg/a3126764-fdd1-42f8-9653-a5170ea5bdef
      Show excerpt
      xenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K vocab is signifigantly worse output at same training but makes sense, model was too lopsided with that much embeddings, but at 100K it did observe intere

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.