AnchorKAN
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
AnchorKAN has 20 facts recorded in Dontopedia across 2 references, with 2 live disagreements.
Mostly:uses domain vocabulary(5), exhibits issue(4), rdf:type(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (11)
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.
measuredValueForModelMeasured Value for Model(7)
- Bpb Metric
ex:bpb-metric - DC 128 Metric
ex:dc-128-metric - S1 Metric
ex:s1-metric - S2 Metric
ex:s2-metric - S3 Metric
ex:s3-metric - S4 Metric
ex:s4-metric - S5 Metric
ex:s5-metric
assertsLocationAsserts Location(1)
- Utterance 5
ex:utterance-5
assessesAssesses(1)
- Utterance 2
ex:utterance-2
comparesToCompares to(1)
- Xenonfun
ex:xenonfun
trainedOnTrained on(1)
- Training Session 2026 03 07
ex:training-session-2026-03-07
Other facts (19)
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.
| Predicate | Value | Ref |
|---|---|---|
| Uses Domain Vocabulary | epistemological | [1] |
| Uses Domain Vocabulary | intentionality | [1] |
| Uses Domain Vocabulary | metaphysics | [1] |
| Uses Domain Vocabulary | logical consequence | [1] |
| Uses Domain Vocabulary | epistemic knowledge | [1] |
| Exhibits Issue | noisy-output | [1] |
| Exhibits Issue | sep-citation-patterns | [1] |
| Exhibits Issue | loops | [1] |
| Exhibits Issue | truncated-names | [1] |
| Rdf:type | Machine Learning Model | [1] |
| Has Parameter Count | 113000000 | [1] |
| Final Perplexity | 65.4 | [1] |
| Best Loss | 3.68 | [1] |
| Vocabulary Size | 8000 | [1] |
| Produces | Philosophical Arguments | [1] |
| Trained From | scratch | [1] |
| Produces Output Type | philosophical-text | [1] |
| Located on | M3 Ultra | [1] |
| Classified As | Soft Attractor Mechanism | [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.
References (2)
ctx:discord/blah/watt-activation/88- full textwatt-activation-88text/plain3 KB
doc:agent/watt-activation-88/0299a1f9-423c-4481-997f-02f201cc0796Show excerpt
[2026-03-07 22:01] xenonfun: ``` ⏺ Training complete. Final results: ┌──────────────────┬───────────────────────────────────────┐ │ Metric │ Value │ ├──────────────────┼──────────────────────…
ctx:discord/blah/watt-activation/374- full textwatt-activation-374text/plain2 KB
doc:agent/watt-activation-374/cb7e122e-3f7b-4f32-9d43-e995d3de2717Show excerpt
[2026-03-18 19:24] xenonfun: ⏺ VQ results in. Head-to-head comparison: ``` ┌─────────────────┬──────────┬───────────┬───────┐ │ Metric │ Baseline │ AnchorKAN │ VQ │ ├─────────────────┼──────────┼───────────┼───────┤ │ S1…
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.