Evidaxis
Dated record

prime-rl

repo · Post-training & Alignment, n = 16 · PrimeIntellect-ai/prime-rl · paper: not linked · as of

30.3 commits/week averaged over the trailing window (niche median 11.95). No paper is linked in OpenAlex. Dependents: no reading in the scored panel. 2,089 GitHub stars, recorded, not scored. Measured for prime-rl as of 2026-09-26; sources: GitHub, OpenAlex and deps.dev where linked.

commits/wk 30.3 averaged, trailing window niche median 11.95 (n = 16) last commit week 2026-09-20 measured · GitHub ·
citations no paper linked all years, indexed to date niche median 11 (n = 4) no reading · OpenAlex ·
direct dependents not in the scored panel partition 2026-09-26 niche median 3 (n = 8) no reading · deps.dev snapshot ·
stars 2,089 recorded, not scored niche median 10,412 (n = 16) measured · GitHub ·
Download values (CSV) JSON record Follow this system (feed) Report an error

Is prime-rl still maintained?

Development velocity is the one measurable axis of three: 30.3 commits per week averaged over the trailing window (niche median 11.95/wk, n = 16).

GitHub averaged 30.3 per week over the trailing window; raw weekly counts below are individual weeks.

Last commit week 2026-09-20.

Commits in the latest captured week vs 4 weeks earlier: -1 · vs 26 weeks earlier: 6 · 52-week range: 8 to 50 commits in an individual week.

line chart: prime-rl, weekly commits, 37 in latest week vs niche median 20, 2025-09-28 to 2026-09-20
prime-rl averaged 30.3 commits a week, 2.5 times the niche median of 11.95. GitHub commit_activity · .
Latest eight weeks
Week startingCommitsNiche P25Niche P75
2026-08-0226022.25
2026-08-0926126.5
2026-08-1650227.75
2026-08-2338036.5
2026-08-3023030.25
2026-09-06181.7527
2026-09-13330.7533.25
2026-09-2037031.75
heatmap chart: prime-rl, weeks with commits, 26 of 26, 2026-03-29 to 2026-09-20
26 of the last 26 captured weeks had commits for prime-rl. GitHub commit_activity · .
All 52 weeks
Weekly commits
Week startingCommits
2025-09-2815
2025-10-0513
2025-10-1212
2025-10-1919
2025-10-2625
2025-11-0235
2025-11-0911
2025-11-1620
2025-11-238
2025-11-3024
2025-12-0714
2025-12-1422
2025-12-2124
2025-12-2819
2026-01-0412
2026-01-1136
2026-01-1831
2026-01-2528
2026-02-0128
2026-02-0827
2026-02-1539
2026-02-2241
2026-03-0131
2026-03-0833
2026-03-1520
2026-03-2231
2026-03-2937
2026-04-0536
2026-04-1234
2026-04-1910
2026-04-2625
2026-05-0328
2026-05-1019
2026-05-1745
2026-05-2433
2026-05-3127
2026-06-0724
2026-06-149
2026-06-2131
2026-06-2836
2026-07-0517
2026-07-1247
2026-07-1931
2026-07-2618
2026-08-0226
2026-08-0926
2026-08-1650
2026-08-2338
2026-08-3023
2026-09-0618
2026-09-1333
2026-09-2037

GitHub commit_activity · period 2025-09-28 to 2026-09-20 · n = 52 weeks · method weekly totals; reconstructed dates · updated · version 9d2fe956adbc-b1 · CSV

Readings

Recorded values and sources
ReadingValueΔ 4 weeksΔ 26 weeks52-week rangeInstrumentDateReproducePrevious reading
Commits per week30.30.90.518.2 to 32.1GitHub, trailing 12 weeks2026-09-26Public query30.2
Citing worksno readingno readingno readingno readingOpenAlex, all years2026-09-26Public queryno reading
Direct dependentsno readingno readingno readingno readingDirect dependents2026-09-26Public queryno reading
Daily dependents (unscored)no readingno readingno readingno readingdeps.dev REST, unscored2026-09-26Public queryno reading
Stars2,089100no reading1,582 to 2,089GitHub stars, unscored2026-09-26Public query2,053

Evidaxis snapshot · period 2026-09-26 · n = 1 system · method source linked readings · updated · version 9d2fe956adbc-b1

How to cite prime-rl's record?

Evidaxis. prime-rl measurement record. Snapshot 2026-09-26. urn:evidaxis:claim:e_H6EVSN8Q85T:m3:2026-09-26. CC0-1.0. https://evidaxis.org/e/e_H6EVSN8Q85T/

Evidaxis · period 2026-09-26 · n = 1 system · method claim URN · updated · version 9d2fe956adbc-b1

How does prime-rl compare with its niche?

16 systems in Post-training & Alignment; niche median 11.95 commits per week. The reader chooses the sort order.

dot plot chart: prime-rl, averaged commits per week, 30.3 vs niche median 11.95, 2026-09-26
prime-rl at 30.3 commits a week among 16 systems; niche median 11.95. GitHub, current cohort · .
All 16 systems, alphabetical; choose a heading to sort
AReaL10no readingno reading5,793
ART14no reading110,778
Axolotl13.9no reading212,506
LLaMA-Factory3.5389475,024
ms-swift27no reading415,731
NeMo-RL32.1no reading12,033
Open R10no readingno reading26,477
Open-Instruct3.1no readingno reading3,879
OpenRLHF3.210no reading10,046
prime-rl30.3no readingno reading2,089
ROLL0.51no reading3,408
Search-R1012no reading5,454
Trinity-RFT0.7no readingno reading703
TRL45.6no reading15319,394
Unsloth272.8no reading2376,834
verl27.4no reading023,643

Evidaxis snapshot · period 2026-09-26 · n = 16 systems · method medians of measured values · updated · version 9d2fe956adbc-b1 · CSV for this niche

What changed since the last snapshot?

2 published readings changed between snapshots fcfd3a7ccdcb and 9d2fe956adbc.

slope chart: prime-rl, changed published values, 2, 2026-09-19 to 2026-09-26
2 published values changed for prime-rl since 2026-09-19. Evidaxis snapshots · .
Snapshot values
MetricPreviousCurrentDelta
Commits per week30.230.30.1
Citing worksno readingno readingno reading
Direct dependentsno readingno readingno reading
Stars2,0532,08936

Evidaxis snapshots · period 2026-09-19 to 2026-09-26 · n = 15 partitions · method paired snapshot values · updated · version 9d2fe956adbc-b1 · History CSV

Take the data or follow changes

Values and captured history are available under CC0-1.0. The system feed records changes to published numbers.

Values CSVHistory CSVJSON recordAtom feedJSON FeedAdd Evidaxis as a preferred source on GoogleReport an error

Evidaxis · period 2026-09-26 · n = 1 system · method CC0-1.0 open export · updated · version 9d2fe956adbc-b1

For teams tracking many systems

Use the cohort CSV, snapshot archive and membership manifest to reproduce observations across systems.

Cohort CSV · Snapshot archive · Membership manifest

Paper and links

Source records identify the system, repository and linked works; no paper authors are published.

What is not measured for prime-rl, and why

Missing readings describe instrument coverage. A missing value is not a measured zero.

Unmeasured slots
ReadingReason
Citing worksnot linked
Direct dependentsoutside panel
Daily dependents (unscored)no reading captured

Dependents: package outside the frozen m3 panel (2026-07-21), a coverage state, not a measured zero. Unscored daily count: no reading (2026-09-26).

Gate ETA: never published; Evidaxis makes no public actionable prediction.

Dependents ecosystem composition: no reading; this field is not present in the snapshot.

Evidaxis · period 2026-09-26 · n = 1 system · method measurement coverage · updated · version 9d2fe956adbc-b1

Measurement detail

Gate, gauges, percentile, derived signals and snapshot receipt

History: 13 weekly observations; minimum 4. Axis coverage: 1 of 3 axes measurable. Gate: not computable - 1 of 3 axes measurable

Gate: not computable - 1 of 3 axes measurable

prime-rl

repo
Post-training & Alignment · n = 16 · PrimeIntellect-ai/prime-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

· Evidaxis snapshot · 2026-09-26
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
· Evidaxis snapshot · 2026-09-26
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+0.96 within cohort, log-slope +0.005/wk.0+0.96
velocity z
+0.96 σ
slope
+0.005/wk
· Evidaxis snapshot · 2026-09-26
log-slope +0.005/wk
citation z Citation source: not measured.
direct-dependents z Direct-dependents axis: outside the frozen panel; not measured.
cohort
16
systems measured
weekly commits
30.3
Development velocity axis: measured.
total citations
no reading
Citation source: not measured.
momentum
62.0
percentile p80
commit heatmap, last 26 weeks30.3/wk
weekly commits, 26 weeks26 weeks of commits, peak 50 in a week, 26 active weeks, 758 total.week 1: 37 commitsweek 2: 36 commitsweek 3: 34 commitsweek 4: 10 commitsweek 5: 25 commitsweek 6: 28 commitsweek 7: 19 commitsweek 8: 45 commitsweek 9: 33 commitsweek 10: 27 commitsweek 11: 24 commitsweek 12: 9 commitsweek 13: 31 commitsweek 14: 36 commitsweek 15: 17 commitsweek 16: 47 commitsweek 17: 31 commitsweek 18: 18 commitsweek 19: 26 commitsweek 20: 26 commitsweek 21: 50 commitsweek 22: 38 commitsweek 23: 23 commitsweek 24: 18 commitsweek 25: 33 commitsweek 26: 37 commits
weeks
26
peak/wk
50
active
26
total
758
· Evidaxis snapshot · 2026-09-26
citations by yearCitation source: not measured.
recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +0.35, regime recent slope below prior window. prior slope +0.013, recent slope +0.005 per week. +0.013prior 39w+0.005recent 13w+0.35×
swing
+0.35×
regime
recent slope below prior window
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value +0.027 with 95% CI +0.008 to +0.046, 50 degrees of freedom. CI excludes zero.0+0.02795% CI +0.008, +0.046+0.008+0.046
sharpe
+0.027
95% ci
+0.008, +0.046
dof
50
snapshot 1 of 1 · · m3
commit changepoint52 weekly commit points. Changepoint at week 50 (2026-09-12), slope change +9.213 commits per week.2026-09-12
date
week
50 of 52
Δslope
+9.213/wk
snapshot 1 of 1 · · m3
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
methodology gate snapshot 1 of 1 · · m3
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 15 of 15 · · m3

Direct-dependents momentum (deps.dev)

Direct-dependents axis: outside the frozen panel; not measured.

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

Reconstructed history

Reconstructed from git history, not a point-in-time capture. This series is separate from captured observations.

sparkline chart: prime-rl, reconstructed commits, 33, 2025-w39 to 2026-w37
prime-rl has 33 reconstructed commits in the latest week; reconstructed niche median not measured. Git history reconstruction · .
Reconstructed weekly commits
PeriodCommits
2025-w3915
2025-w4013
2025-w4112
2025-w4219
2025-w4325
2025-w4435
2025-w4511
2025-w4620
2025-w478
2025-w4824
2025-w4914
2025-w5022
2025-w5124
2025-w5219
2026-w0112
2026-w0236
2026-w0331
2026-w0428
2026-w0528
2026-w0627
2026-w0739
2026-w0841
2026-w0931
2026-w1033
2026-w1120
2026-w1231
2026-w1337
2026-w1436
2026-w1534
2026-w1610
2026-w1725
2026-w1828
2026-w1919
2026-w2045
2026-w2133
2026-w2227
2026-w2324
2026-w249
2026-w2531
2026-w2636
2026-w2717
2026-w2847
2026-w2931
2026-w3018
2026-w3126
2026-w3226
2026-w3350
2026-w3438
2026-w3523
2026-w3618
2026-w3733
Peer signals
SystemMomentumPercentile
AReaL46.747
ART76.4100
Axolotl52.560
LLaMA-Factory29.20
ms-swift52.453
NeMo-RL74.693
Open R142.540
Open-Instruct30.97
OpenRLHF41.133
prime-rl6280
ROLL38.913
Search-R154.273
Trinity-RFT39.920
TRL52.567
Unsloth62.687
verl40.427

Evidaxis · period 2026-09-26 · n = 1 system · method measurement detail · updated · version 9d2fe956adbc-b1 · record JSON · snapshot receipt