Evidaxis

As of 2026-10-10: Diffusers (Media Generation) is under weekly measurement. Axis coverage: 2 of 3 axes measurable. Gate: not computable — reference measurement

Diffusers

repo reference measurement
Media Generation · n = 15 · huggingface/diffusers
2 of 3 axes measurable · conf medium
convergence gate
Convergence gate: Gate: not computable — reference measurement Development velocity: measured × Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): measured ×
gate
0 of 3 axes

Gate: not computable — reference measurement

Gate: not computable — reference measurement
position in cohort distribution one of 15 in cohort
percentile 7 within cohort p25 p50 p75 p0 p100
percentile
p7
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z-2.50 within cohort, log-slope -0.011/wk.0-2.50
velocity z
-2.50 σ
slope
-0.011/wk
log-slope -0.011/wk
citation z Citation source: not measured.
direct-dependents z
direct-dependents z gaugedirect-dependents z+0.00 within cohort, log-slope +0.008/point.0+0.00
direct-dependents z
+0.00 σ
slope
+0.008/point
Direct-dependents axis: measured.
cohort
15
systems measured
weekly commits
21.1
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
34.4
percentile p7
commit heatmap, last 26 weeks21.1/wk
weekly commits, 26 weeks26 weeks of commits, peak 48 in a week, 26 active weeks, 547 total.week 1: 12 commitsweek 2: 14 commitsweek 3: 19 commitsweek 4: 26 commitsweek 5: 18 commitsweek 6: 15 commitsweek 7: 30 commitsweek 8: 28 commitsweek 9: 25 commitsweek 10: 16 commitsweek 11: 17 commitsweek 12: 17 commitsweek 13: 30 commitsweek 14: 27 commitsweek 15: 29 commitsweek 16: 22 commitsweek 17: 25 commitsweek 18: 28 commitsweek 19: 48 commitsweek 20: 22 commitsweek 21: 8 commitsweek 22: 14 commitsweek 23: 16 commitsweek 24: 20 commitsweek 25: 17 commitsweek 26: 4 commits
weeks
26
peak/wk
48
active
26
total
547
citations by yearCitation source: not measured.
Daily dependents count (unscored) 402 dependents 328 direct, 76 indirect · pypi/diffusers · deps.dev · the scored m4 axis uses weekly partitions

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 -10.60, regime recent slope sign differs from prior window. prior slope +0.009, recent slope -0.096 per week. +0.009prior 39w-0.096recent 13w-10.60×
swing
-10.60×
regime
recent slope sign differs from prior window
windows
13w vs 39w
snapshot 1 of 1 · · m4
commit-axis Sharpe log-linear slope over residual std, value +0.006 with 95% CI -0.015 to +0.028, 50 degrees of freedom. CI spans zero.0+0.00695% CI -0.015, +0.028-0.015+0.028
sharpe
+0.006
95% ci
-0.015, +0.028
dof
50
snapshot 1 of 1 · · m4
commit changepoint52 weekly commit points. Changepoint at week 50 (2026-09-26), slope change -8.116 commits per week.2026-09-26
date
week
50 of 52
Δslope
-8.116/wk
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

Diffusers reconstructed weekly commits52 points, range 1 to 55 commits/wk.
min
1 commits/wk
max
55 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.

Daily dependents count (unscored)

Diffusers dependents over time15 points, range 386 to 433 dependents.
min
386 dependents
max
433 dependents
latest
402 dependents
points
15

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

Measurement states

Diffusers is under weekly measurement. History: 15 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: measured. Gate: not computable — reference measurement

Sources

huggingface/diffusers development-velocity axis

Others in Media Generation

ACE-Step Media Generation
1 of 3 axes measurable
43
p21
vel -0.54 cit no axis deps no axis
axis dials
-0.54 n/a n/a
ComfyUI Media Generation
1 of 3 axes measurable
24
p0
vel -2.06 cit no axis deps no axis
axis dials
-2.06 n/a n/a
Fish Speech Media Generation
1 of 3 axes measurable
93
p100
vel +3.47 cit no axis deps no axis
axis dials
+3.47 n/a n/a
FLUX.1 Media Generation
1 of 3 axes measurable
54
p57
vel +0.34 cit no axis deps no axis
axis dials
+0.34 n/a n/a
HunyuanVideo Media Generation
1 of 3 axes measurable
87
p86
vel +2.96 cit no axis deps no axis
axis dials
+2.96 n/a n/a
Kokoro-82M Media Generation
2 of 3 axes measurable
45
p29
vel -0.20 cit no axis deps -0.67
axis dials
-0.20 n/a -0.67

Full Media Generation cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state
scored
Cohort z
+0.00
OLS slope
+0.008
Theil-Sen slope
+0.008
Latest direct dependents
383
Confirmed-clean points
26
Reconstructed history points
15
As-of partition
2026-09-28
Fragility veto
inactive
Rising vote
no

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

Cite this measurement

Plain citation

Evidaxis. Diffusers measurement record. Snapshot 2026-10-10. https://evidaxis.org/e/e_9VRK70WNP96/ Concept DOI: 10.5281/zenodo.21076011.

BibTeX

@dataset{evidaxis_e_9VRK70WNP96_20261010,
  title = {Diffusers measurement record},
  publisher = {Evidaxis},
  year = {2026},
  url = {https://evidaxis.org/e/e_9VRK70WNP96/},
  doi = {10.5281/zenodo.21076011}
}

Download record (JSON)

entity_id e_9VRK70WNP96 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, Diffusers, entity e_9VRK70WNP96, snapshot 2026-w41.”

Durable reference (format-independent): urn:evidaxis:claim:e_9VRK70WNP96:m4:2026-10-10