Evidaxis

Trinity-RFT

repo
Post-training & Alignment · n = 14 · agentscope-ai/Trinity-RFT
Single-axis · conf low
momentum
momentum 60.6 of 100 60.6 /100
momentum
60.6/100
pctile
p85
convergence gate
Convergence gate: velocity only, citation axis absent × ∅
gate
0 of 2 axes

velocity only, citation axis absent.

gate shut
position in cohort distribution one of 14 in cohort
percentile 85 within cohort p25 p50 p75 p0 p100
percentile
p85
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+0.85 within cohort, log-slope +0.005/wk.0+0.85
velocity z
+0.85 σ
slope
+0.005/wk
log-slope +0.005/wk
convergence planefull gate = rising
Trinity-RFT on the convergence plane Trinity-RFT at velocity z +0.85 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
+0.85
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
4.4
not rising
total citations
n/a
no axis
momentum
60.6
percentile p85
commit heatmap, last 26 weeks4.4/wk
weekly commits, 26 weeks26 weeks of commits, peak 11 in a week, 22 active weeks, 86 total.week 1: 9 commitsweek 2: 0 commitsweek 3: 2 commitsweek 4: 2 commitsweek 5: 2 commitsweek 6: 0 commitsweek 7: 2 commitsweek 8: 2 commitsweek 9: 5 commitsweek 10: 0 commitsweek 11: 2 commitsweek 12: 1 commitsweek 13: 2 commitsweek 14: 4 commitsweek 15: 7 commitsweek 16: 11 commitsweek 17: 10 commitsweek 18: 3 commitsweek 19: 7 commitsweek 20: 7 commitsweek 21: 2 commitsweek 22: 1 commitsweek 23: 1 commitsweek 24: 3 commitsweek 25: 1 commitsweek 26: 0 commits
weeks
26
peak/wk
11
active
22
total
86
citations by yearno axis
adoption 0 dependents 0 direct · pypi/trinity-rft · deps.dev · adoption signal, not part of the momentum score

Trinity-RFT holds an Evidaxis momentum score of 60.6 of 100 on methodology m2, snapshot 2026-08-08, measured within the Post-training & Alignment cohort (n = 14). No axis is currently rising within the cohort, and no second (citation) axis is available, 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 +3.35, regime accelerating. prior slope -0.047, recent slope -0.156 per week. -0.047prior 39w-0.156recent 13w+3.35×
swing
+3.35×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value -0.044 with 95% CI -0.070 to -0.018, 50 degrees of freedom. CI spans zero.0-0.04495% CI -0.070, -0.018-0.070-0.018
sharpe
-0.044
95% ci
-0.070, -0.018
dof
50
snapshot 1 of 1 · · m2
commit changepoint52 weekly commit points. Changepoint at week 50 (2026-07-25), slope change -1.324 commits per week.2026-07-25
date
week
50 of 52
Δslope
-1.324/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

Adoption trend

Trinity-RFT dependents over time6 points, range 0 to 0 dependents.
min
0 dependents
max
0 dependents
latest
0 dependents
points
6

Downstream packages depending on pypi/trinity-rft (deps.dev), captured point-in-time each snapshot. An adoption signal, not part of the momentum score.

Verdict

Trinity-RFT is tracked. No axis is currently rising relative to its cohort, and it has no second (citation) axis available.

Path to Rising: needs development velocity to recover (at least 5 commits per week and a positive within-cohort slope); a second measurable axis to exist (no academic paper is currently tracked).

Sources

agentscope-ai/Trinity-RFT development-velocity axis
OpenAlex paper citation-momentum axis

Embed this badge

Evidaxis single-axis, Trinity-RFT
[![Evidaxis: Trinity-RFT](https://evidaxis.org/badge/e_DQT3XHMXA2C/2026-w32.svg)](https://evidaxis.org/e/e_DQT3XHMXA2C)

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
NeMo-RL Post-training & Alignment
Watch
88
p100
vel +3.01 cit no axis
axis dials
+3.01 n/a
Open R1 Post-training & Alignment
Single-axis
53
p62
vel +0.23 cit no axis
axis dials
+0.23 n/a

Full Post-training & Alignment cohort →

entity_id e_DQT3XHMXA2C 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, Trinity-RFT, entity e_DQT3XHMXA2C, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_DQT3XHMXA2C:m2:2026-08-08