Evidaxis

Unsloth

repo
Post-training & Alignment · n = 16 · unslothai/unsloth
Rising · conf high
convergence gate
Convergence gate: Convergence gate: evaluated weekly; Rising signal published for 2026-w41. Development velocity: rising vote Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): rising vote
gate
2 of 3 axes

Convergence gate: evaluated weekly; Rising signal published for 2026-w41.

Convergence gate: evaluated weekly; Rising signal published for 2026-w41.
position in cohort distribution one of 16 in cohort
percentile 100 within cohort p25 p50 p75 p0 p100
percentile
p100
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+2.12 within cohort, log-slope +0.094/wk.0+2.12
velocity z
+2.12 σ
slope
+0.094/wk
log-slope +0.094/wk
citation z Citation source: not measured.
direct-dependents z
direct-dependents z gaugedirect-dependents z+3.00 within cohort, log-slope +0.009/point.0+3.00
direct-dependents z
+3.00 σ
slope
+0.009/point
Direct-dependents axis: measured.
cohort
16
systems measured
weekly commits
641.2
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
82.0
percentile p100
commit heatmap, last 26 weeks641.2/wk
weekly commits, 26 weeks26 weeks of commits, peak 1045 in a week, 26 active weeks, 10116 total.week 1: 69 commitsweek 2: 38 commitsweek 3: 92 commitsweek 4: 134 commitsweek 5: 238 commitsweek 6: 100 commitsweek 7: 119 commitsweek 8: 367 commitsweek 9: 218 commitsweek 10: 263 commitsweek 11: 146 commitsweek 12: 221 commitsweek 13: 159 commitsweek 14: 258 commitsweek 15: 408 commitsweek 16: 610 commitsweek 17: 769 commitsweek 18: 530 commitsweek 19: 626 commitsweek 20: 427 commitsweek 21: 463 commitsweek 22: 736 commitsweek 23: 877 commitsweek 24: 1045 commitsweek 25: 1032 commitsweek 26: 171 commits
weeks
26
peak/wk
1045
active
26
total
10116
citations by yearCitation source: not measured.
Daily dependents count (unscored) 24 dependents 24 direct · pypi/unsloth · deps.dev · the scored m4 axis uses weekly partitions

Unsloth holds an Evidaxis momentum score of 82.0 of 100 on methodology m4, snapshot 2026-10-10, measured within the Post-training & Alignment cohort (n = 16). Axis coverage: 2 of 3 axes measurable. Convergence gate: evaluated weekly; Rising signal published for 2026-w41.

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 +0.50, regime recent slope below prior window. prior slope +0.055, recent slope +0.028 per week. +0.055prior 39w+0.028recent 13w+0.50×
swing
+0.50×
regime
recent slope below prior window
windows
13w vs 39w
snapshot 1 of 1 · · m4
commit-axis Sharpe log-linear slope over residual std, value +0.094 with 95% CI +0.064 to +0.123, 50 degrees of freedom. CI excludes zero.0+0.09495% CI +0.064, +0.123+0.064+0.123
sharpe
+0.094
95% ci
+0.064, +0.123
dof
50
snapshot 1 of 1 · · m4
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 · · m4
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m4
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m4
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m4
methodology gate snapshot 1 of 1 · · m4
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 · · m4

Reconstructed history

Unsloth reconstructed weekly commits52 points, range 3 to 425 commits/wk.
min
3 commits/wk
max
425 commits/wk
latest
25 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.

Daily dependents count (unscored)

Unsloth dependents over time14 points, range 4 to 24 dependents.
min
4 dependents
max
24 dependents
latest
24 dependents
points
14

Downstream packages depending on pypi/unsloth (deps.dev), captured point-in-time each snapshot. This daily series is unscored. The scored axis in m4 uses weekly partitions.

Measurement states

Unsloth is under weekly measurement. History: 13 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: measured. Convergence gate: evaluated weekly; Rising signal published for 2026-w41.

Sources

unslothai/unsloth development-velocity axis
unsloth.ai homepage

Embed this badge

Evidaxis Rising, Unsloth
[![Evidaxis: Unsloth](https://evidaxis.org/badge/e_J16JY8N155H/2026-w41.svg)](https://evidaxis.org/e/e_J16JY8N155H)

Others in Post-training & Alignment

AReaL Post-training & Alignment
1 of 3 axes measurable
47
p40
vel -0.27 cit no axis deps no axis
axis dials
-0.27 n/a n/a
ART Post-training & Alignment
1 of 3 axes measurable
66
p93
vel +1.31 cit no axis deps no axis
axis dials
+1.31 n/a n/a
Axolotl Post-training & Alignment
1 of 3 axes measurable
56
p73
vel +0.45 cit no axis deps no axis
axis dials
+0.45 n/a n/a
LLaMA-Factory Post-training & Alignment
1 of 3 axes measurable
24
p0
vel -2.06 cit no axis deps no axis
axis dials
-2.06 n/a n/a
ms-swift Post-training & Alignment
2 of 3 axes measurable
43
p33
vel -0.48 cit no axis deps -0.67
axis dials
-0.48 n/a -0.67
NeMo-RL Post-training & Alignment
1 of 3 axes measurable
66
p87
vel +1.29 cit no axis deps no axis
axis dials
+1.29 n/a n/a

Full Post-training & Alignment cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state
scored
Cohort z
+3.00
OLS slope
+0.009
Theil-Sen slope
+0.003
Latest direct dependents
21
Confirmed-clean points
26
Reconstructed history points
15
As-of partition
2026-09-28
Fragility veto
inactive
Rising vote
yes

This axis measures the trajectory of a system's own packages: declared in its own tree, published under that name, and not attributed by deps.dev to another repository. A package with no repository link is unverified and stays. The self-name exclusion list is fixed at the v2h.1 panel. Systems with no admitted package are not measured on this axis. Points that cannot be derived exactly are withheld, and the series restarts after a withheld point.

The earliest weekly points of each series were read from deps.dev's BigQuery history on 2026-07-21; later points are weekly captures. m4 does not replay those partitions: each point is the stored system total, one package's unique_direct, or a complete sketch union, and a point that is not exact is withheld. Each record reports how many of its points are reconstructed history.

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_J16JY8N155H methodology m4 snapshot ad5e404d4f82 period 2026-w41 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m4, never edited by hand. Cite as: “Evidaxis, Unsloth, entity e_J16JY8N155H, snapshot 2026-w41.”

Durable reference (format-independent): urn:evidaxis:claim:e_J16JY8N155H:m4:2026-10-10