Factual Recall
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Factual Recall has 2 facts recorded in Dontopedia across 2 references.
Maturity scale
raw canonical shape-checked rule-derived certifiedMeasured at PplmeasuredAtPpl
- 242[1]all time · Part 172
Rdfs:labelrdfs:label
- factual recall[2]all time · 178
Inbound mentions (9)
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.
advisesLeaveFactualRecallAdvises Leave Factual Recall(1)
- Message 2026 03 10 00 52
ex:message-2026-03-10-00-52
determinesRecallCapacityDetermines Recall Capacity(1)
- Parameter Count
ex:parameter-count
doesNotTeachDoes Not Teach(1)
- Fineweb Edu
ex:fineweb-edu
doesNotTeachFactualRecallDoes Not Teach Factual Recall(1)
- Fineweb Edu
ex:fineweb-edu
hasWeakHas Weak(1)
- Model
ex:model
presupposesModelFineTuningNeedPresupposes Model Fine Tuning Need(1)
- Chat Context
ex:chat-context
rejectsFactualRecallNowRejects Factual Recall Now(1)
- Lisamegawatts
ex:lisamegawatts
responsibleForResponsible for(1)
- Different Architecture
ex:different-architecture
suggestsDelegatingSuggests Delegating(1)
- Xenonfun
ex:xenonfun
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.
References (2)
- custom
ctx:discord/blah/watt-activation/part-172 - custom
ctx:discord/blah/watt-activation/178- full textwatt-activation-178text/plain3 KB
doc:agent/watt-activation-178/50ec323b-637a-4c18-bba8-73839dc1355dShow excerpt
[2026-03-10 00:29] xenonfun: ⏺ That settles it — the base instruct model has no factual knowledge at all. It generates fluent-sounding nonsense rather than facts. This is a pretraining depth problem: FineWeb-Edu teaches language patterns,…
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.