R Global
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
R Global has 20 facts recorded in Dontopedia across 6 references.
20 facts·20 predicates·6 sources
Mostly:status(1), value(1), measured at(1)
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
R Global has 20 facts recorded in Dontopedia across 6 references.
Mostly:status(1), value(1), measured at(1)
hasValueAtTimestepexhibitsBehaviorvalueInContextsourceOfValuevalueCurrentlyvalueAtCommitsourceCurrentlyOther 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.
includesIncludes(1)ex:harmonic-feature-dimsinvolvesMetricInvolves Metric(1)ex:correct-denoising-trajectoryThe 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 |
|---|---|---|
| Default Value | 0.5 | [1] |
| Source at Commit | attention gates | [1] |
| Rdfs:label | r_global | [1] |
| Has Shape | (B, T, 1) | [4] |
| Stored in | Last Metrics | [6] |
| Type of | Metric Data | [6] |
| Part of Group | Monitoring Trio | [3] |
| Has Semantic Role | Order Indicator | [3] |
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.
doc:agent/watt-activation-195/9d5afb8d-40fb-44fa-9517-0103dc5aafc5[2026-03-10 05:05] xenonfun: ⏺ Phase metrics are already logged every step — extract_block_metrics is called each step with full=True only every 100 (for the heavier entropy/power computations). So maximum useful cadence is already there. a…
doc:agent/watt-activation-272/8fae39f3-3d21-4cc2-ae01-bb6475aad90b[2026-03-13 19:02] xenonfun: ``` ⏺ The architecture is sound — the three core bugs are fixed. Here's the honest picture: What's working: - Independent text encoding (_encode_text_per_layer) — r_cross=0.02, no sync contamination - Per…
doc:agent/watt-activation-182/68d54e39-55f1-4bc9-a8b7-cf0fd9466f04[2026-03-10 01:54] xenonfun: smoketests before any other changes, see if they actually do things now. (files: Screenshot_2026-03-09_at_9.54.29_PM.png) [2026-03-10 01:56] xenonfun: and its doing proper vals this time [2026-03-10 01:57] lisam…
doc:agent/watt-activation-185/fcee3d0e-68fc-4f0b-ad9d-157115bfbade[2026-03-10 02:38] lisamegawatts: i think this part is wrong, it should not init at zero they need frequencies. i also don't think it needs gelu, the linear error is inherently in the sphere; The Lohe sphere model, a generalization of the K…
doc:agent/watt-activation-405/a6ab8777-b42b-4fbf-84c0-44e6d6031c2c[2026-03-19 06:06] xenonfun: so on a per iteration its lower loss, but that is unfar as it has seem way more data. suppose need something like delta(loss)/delta(bytes_seen) [2026-03-19 06:08] xenonfun: ⏺ Good analysis. The dashboard should …
doc:agent/watt-activation-184/bd60859b-3b94-475c-ba0c-71544048a50a[2026-03-10 02:24] xenonfun: # Data flows real extraction costs of metrics (files: Screenshot_2026-03-09_at_10.24.28_PM.png) [2026-03-10 02:31] lisamegawatts: also for the non zero init, it should be frequencies [2026-03-10 02:31] lisamegaw…
Dontopedia is in a read-only public launch. Follow the references and disputed branches now; contributions will open after durable identity and moderation are in place.