Evidaxis

NeMo-RL

repo
Post-training & Alignment · n = 14 · NVIDIA-NeMo/RL
Watch · conf low
momentum
momentum 87.7 of 100 87.7 /100
momentum
87.7/100
pctile
p100
convergence gate
Convergence gate: velocity only, citation axis absent ∅
gate
1 of 2 axes

velocity only, citation axis absent.

one axis passes
position in cohort distribution one of 14 in cohort
percentile 100 within cohort p25 p50 p75 p0 p100
percentile
p100
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+3.01 within cohort, log-slope +0.047/wk.0+3.01
velocity z
+3.01 σ
slope
+0.047/wk
log-slope +0.047/wk
convergence planefull gate = rising
NeMo-RL on the convergence plane NeMo-RL at velocity z +3.01 and citation z no axis, against 0 dual-axis cohort peers. single-axis: citation axis absent, excluded from the plane. z>=1 median velocity z → citation z ↑
velocity z
+3.01
citation z
no axis
peers
13

single-axis: citation axis absent, excluded from the plane.

citation z no citation axis
cohort
14
systems measured
weekly commits
31.4
rising trend
total citations
n/a
no axis
momentum
87.7
percentile p100
commit heatmap, last 26 weeks31.4/wk
weekly commits, 26 weeks26 weeks of commits, peak 47 in a week, 26 active weeks, 574 total.week 1: 21 commitsweek 2: 11 commitsweek 3: 9 commitsweek 4: 11 commitsweek 5: 9 commitsweek 6: 15 commitsweek 7: 10 commitsweek 8: 28 commitsweek 9: 20 commitsweek 10: 16 commitsweek 11: 11 commitsweek 12: 11 commitsweek 13: 9 commitsweek 14: 16 commitsweek 15: 17 commitsweek 16: 34 commitsweek 17: 23 commitsweek 18: 42 commitsweek 19: 23 commitsweek 20: 47 commitsweek 21: 36 commitsweek 22: 39 commitsweek 23: 36 commitsweek 24: 25 commitsweek 25: 26 commitsweek 26: 29 commits
weeks
26
peak/wk
47
active
26
total
574
citations by yearno axis

NeMo-RL holds an Evidaxis momentum score of 87.7 of 100 on methodology m2, snapshot 2026-08-08, measured within the Post-training & Alignment cohort (n = 14). Its development-velocity axis is rising within the cohort while a second independent axis has not converged, so it sits below the two-axis gate.

Derived signals

second-order reads, computed from the published series

Three signals ship when the commit series is statistically sufficient; the rest are held in a reserved state until the data supports them. A reserved signal shows its reason, never a fabricated number. How these are computed.

recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio -11.66, regime reversing. prior slope -0.003, recent slope +0.032 per week. -0.003prior 39w+0.032recent 13w-11.66×
swing
-11.66×
regime
reversing
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value +0.033 with 95% CI +0.005 to +0.060, 50 degrees of freedom. CI excludes zero.0+0.03395% CI +0.005, +0.060+0.005+0.060
sharpe
+0.033
95% ci
+0.005, +0.060
dof
50
snapshot 1 of 1 · · m2
commit changepoint52 weekly commit points. Changepoint at week 4 (2025-09-06), slope change -6.610 commits per week.2025-09-06
date
week
4 of 52
Δslope
-6.610/wk
snapshot 1 of 1 · · m2
code-leads-citation lag reserved

reserved: citation series too short / axis absent for cross-correlation

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
axis alpha vs cohort reserved

reserved: cohort N too small for regression (power ~0)

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m2
methodology gate snapshot 1 of 1 · · m2
commit weeks
52
citation years
0
shipped
3
reserved
3

shipped

  • recency-swing
  • commit-sharpe
  • commit-changepoint

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m2

Verdict

NeMo-RL is rising on development velocity, but a second independent axis has not yet converged. It is on watch.

Path to Rising: needs a second measurable axis to exist (no academic paper is currently tracked).

Sources

NVIDIA-NeMo/RL development-velocity axis

Embed this badge

Evidaxis watch, NeMo-RL
[![Evidaxis: NeMo-RL](https://evidaxis.org/badge/e_QHYA574DXDQ/2026-w32.svg)](https://evidaxis.org/e/e_QHYA574DXDQ)

Others in Post-training & Alignment

AReaL Post-training & Alignment
Single-axis
21
p23
vel -2.31 cit no axis
axis dials
-2.31 n/a
Axolotl Post-training & Alignment
Single-axis
47
p38
vel -0.24 cit no axis
axis dials
-0.24 n/a
LLaMA-Factory Post-training & Alignment
Single-axis
50
p46
vel -0.01 cit no axis
axis dials
-0.01 n/a
ms-swift Post-training & Alignment
Single-axis
50
p54
vel -0.02 cit no axis
axis dials
-0.02 n/a
Open R1 Post-training & Alignment
Single-axis
53
p62
vel +0.23 cit no axis
axis dials
+0.23 n/a
Open-Instruct Post-training & Alignment
Single-axis
13
p8
vel -2.99 cit no axis
axis dials
-2.99 n/a

Full Post-training & Alignment cohort →

entity_id e_QHYA574DXDQ methodology m2 snapshot 035a72a81e59 period 2026-w32 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m2, never edited by hand. Cite as: “Evidaxis, NeMo-RL, entity e_QHYA574DXDQ, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_QHYA574DXDQ:m2:2026-08-08