Evidaxis

NeMo-RL

repo
Post-training & Alignment · n = 16 · NVIDIA-NeMo/RL
1 of 3 axes measurable · conf low
convergence gate
Convergence gate: Gate: not computable — 1 of 3 axes measurable Development velocity: measured × Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): not measurable ∅
gate
0 of 3 axes

Gate: not computable — 1 of 3 axes measurable

Gate: not computable — 1 of 3 axes measurable
position in cohort distribution one of 16 in cohort
percentile 80 within cohort p25 p50 p75 p0 p100
percentile
p80
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+0.84 within cohort, log-slope +0.026/wk.0+0.84
velocity z
+0.84 σ
slope
+0.026/wk
log-slope +0.026/wk
citation z Citation source: not measured.
direct-dependents z Direct-dependents axis: no admitted own package; not measured.
cohort
16
systems measured
weekly commits
41.5
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
60.5
percentile p80
commit heatmap, last 26 weeks41.5/wk
weekly commits, 26 weeks26 weeks of commits, peak 70 in a week, 26 active weeks, 919 total.week 1: 16 commitsweek 2: 17 commitsweek 3: 34 commitsweek 4: 23 commitsweek 5: 42 commitsweek 6: 23 commitsweek 7: 47 commitsweek 8: 36 commitsweek 9: 39 commitsweek 10: 36 commitsweek 11: 25 commitsweek 12: 26 commitsweek 13: 29 commitsweek 14: 28 commitsweek 15: 33 commitsweek 16: 44 commitsweek 17: 30 commitsweek 18: 36 commitsweek 19: 34 commitsweek 20: 25 commitsweek 21: 28 commitsweek 22: 54 commitsweek 23: 70 commitsweek 24: 48 commitsweek 25: 48 commitsweek 26: 48 commits
weeks
26
peak/wk
70
active
26
total
919
citations by yearCitation source: not measured.

NeMo-RL holds an Evidaxis momentum score of 60.5 of 100 on methodology m5, snapshot 2026-11-07, measured within the Post-training & Alignment cohort (n = 16). Axis coverage: 1 of 3 axes measurable. Gate: not computable — 1 of 3 axes measurable

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 +1.20, regime accelerating. prior slope +0.039, recent slope +0.046 per week. +0.039prior 39w+0.046recent 13w+1.20×
swing
+1.20×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m5
commit-axis Sharpe log-linear slope over residual std, value +0.088 with 95% CI +0.068 to +0.107, 50 degrees of freedom. CI excludes zero.0+0.08895% CI +0.068, +0.107+0.068+0.107
sharpe
+0.088
95% ci
+0.068, +0.107
dof
50
snapshot 1 of 1 · · m5
commit changepoint52 weekly commit points. No significant changepoint detected (|delta slope| within the noise floor).no significant changepoint
changepoint
none detected
snapshot 1 of 1 · · m5
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m5
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m5
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m5
methodology gate snapshot 1 of 1 · · m5
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 · · m5

Reconstructed history

NeMo-RL reconstructed weekly commits52 points, range 1 to 47 commits/wk.
min
1 commits/wk
max
47 commits/wk
latest
1 commits/wk
points
52

Weekly commits over the past year, reconstructed from git history (GitHub commit_activity). This is reconstructed, not a point-in-time capture. Evidaxis captures the Type-2 signals (watchers, issues, dependents) live and never backfills them; those are the moat.

Measurement states

NeMo-RL is under weekly measurement. History: 18 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: no admitted own package; not measured. Gate: not computable — 1 of 3 axes measurable

Sources

NVIDIA-NeMo/RL development-velocity axis

Others in Post-training & Alignment

AReaL Post-training & Alignment
1 of 3 axes measurable
59
p73
vel +0.68 cit no axis deps no axis
axis dials
+0.68 n/a n/a
ART Post-training & Alignment
1 of 3 axes measurable
55
p60
vel +0.37 cit no axis deps no axis
axis dials
+0.37 n/a n/a
Axolotl Post-training & Alignment
1 of 3 axes measurable
57
p67
vel +0.53 cit no axis deps no axis
axis dials
+0.53 n/a n/a
LLaMA-Factory Post-training & Alignment
1 of 3 axes measurable
16
p0
vel -2.75 cit no axis deps no axis
axis dials
-2.75 n/a n/a
ms-swift Post-training & Alignment
2 of 3 axes measurable
40
p27
vel -0.88 cit no axis deps -0.67
axis dials
-0.88 n/a -0.67
Open R1 Post-training & Alignment
1 of 3 axes measurable
41
p40
vel -0.71 cit no axis deps no axis
axis dials
-0.71 n/a n/a

Full Post-training & Alignment cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: no admitted own package; not measured.

Coverage state
out_of_panel
Cohort z
no axis
OLS slope
n/a
Theil-Sen slope
n/a
Latest direct dependents
n/a
Confirmed-clean points
n/a
Reconstructed history points
n/a
As-of partition
n/a
Fragility veto
n/a
Rising vote
no

Source: deps.dev (Google), CC-BY 4.0. Modified: aggregated to system-level counts and momentum scores.

Axis definition · Snapshot axis correlations

entity_id e_QHYA574DXDQ methodology m5 snapshot 868e3c39d9c7 period 2026-w45 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m5, never edited by hand. Cite as: “Evidaxis, NeMo-RL, entity e_QHYA574DXDQ, snapshot 2026-w45.”

Durable reference (format-independent): urn:evidaxis:claim:e_QHYA574DXDQ:m5:2026-11-07