Evidaxis

DSPy

repo
Agent Frameworks · n = 17 · stanfordnlp/dspy
2 of 3 axes measurable · conf medium
convergence gate
Convergence gate: Gate: computed weekly across the cohort; no convergence event this week Development velocity: rising vote Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): measured ×
gate
1 of 3 axes

Gate: computed weekly across the cohort; no convergence event this week

Gate: computed weekly across the cohort; no convergence event this week
position in cohort distribution one of 17 in cohort
percentile 62 within cohort p25 p50 p75 p0 p100
percentile
p62
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+1.18 within cohort, log-slope +0.033/wk.0+1.18
velocity z
+1.18 σ
slope
+0.033/wk
log-slope +0.033/wk
citation z Citation axis: insufficient source coverage (source returned too few observations).
direct-dependents z
direct-dependents z gaugedirect-dependents z-0.40 within cohort, log-slope +0.017/point.0-0.40
direct-dependents z
-0.40 σ
slope
+0.017/point
Direct-dependents axis: measured.
cohort
17
systems measured
weekly commits
13.5
Development velocity axis: measured.
total citations
n/a
Citation axis: insufficient source coverage (source returned too few observations).
momentum
54.9
percentile p62
commit heatmap, last 26 weeks13.5/wk
weekly commits, 26 weeks26 weeks of commits, peak 26 in a week, 24 active weeks, 287 total.week 1: 1 commitsweek 2: 0 commitsweek 3: 19 commitsweek 4: 15 commitsweek 5: 17 commitsweek 6: 12 commitsweek 7: 14 commitsweek 8: 8 commitsweek 9: 20 commitsweek 10: 6 commitsweek 11: 10 commitsweek 12: 2 commitsweek 13: 0 commitsweek 14: 1 commitsweek 15: 3 commitsweek 16: 20 commitsweek 17: 4 commitsweek 18: 12 commitsweek 19: 15 commitsweek 20: 13 commitsweek 21: 23 commitsweek 22: 24 commitsweek 23: 4 commitsweek 24: 8 commitsweek 25: 26 commitsweek 26: 10 commits
weeks
26
peak/wk
26
active
24
total
287
citations by yearCitation axis: insufficient source coverage (source returned too few observations).
Daily dependents count (unscored) 262 dependents 173 direct, 94 indirect · pypi/dspy · deps.dev · the scored m3 axis uses weekly partitions

DSPy holds an Evidaxis momentum score of 54.9 of 100 on methodology m3, snapshot 2026-09-26, measured within the Agent Frameworks cohort (n = 17). Axis coverage: 2 of 3 axes measurable. Gate: computed weekly across the cohort; no convergence event this week

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 -48.41, regime recent slope sign differs from prior window. prior slope -0.002, recent slope +0.099 per week. -0.002prior 39w+0.099recent 13w-48.41×
swing
-48.41×
regime
recent slope sign differs from prior window
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value +0.010 with 95% CI -0.014 to +0.034, 50 degrees of freedom. CI spans zero.0+0.01095% CI -0.014, +0.034-0.014+0.034
sharpe
+0.010
95% ci
-0.014, +0.034
dof
50
snapshot 1 of 1 · · m3
commit changepoint52 weekly commit points. Changepoint at week 4 (2025-10-25), slope change +4.655 commits per week.2025-10-25
date
week
4 of 52
Δslope
+4.655/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
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m3
methodology gate snapshot 1 of 1 · · m3
commit weeks
52
citation years
3
shipped
3
reserved
3

shipped

  • recency-swing
  • commit-sharpe
  • commit-changepoint

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m3

Reconstructed history

DSPy reconstructed weekly commits49 points, range 1 to 26 commits/wk.
min
1 commits/wk
max
26 commits/wk
latest
26 commits/wk
points
49

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)

DSPy dependents over time13 points, range 254 to 265 dependents.
min
254 dependents
max
265 dependents
latest
262 dependents
points
13

Downstream packages depending on pypi/dspy (deps.dev), captured point-in-time each snapshot. This daily series is unscored. The scored axis in m3 uses weekly partitions.

Measurement states

DSPy is under weekly measurement. History: 13 weekly observations; minimum 4. Development velocity axis: measured. Citation axis: insufficient source coverage (source returned too few observations). Direct-dependents axis: measured. Gate: computed weekly across the cohort; no convergence event this week

Sources

stanfordnlp/dspy development-velocity axis
OpenAlex paper citation-momentum axis
dspy.ai homepage

Others in Agent Frameworks

AgentScope Agent Frameworks
Rising
80
p100
vel +2.83 cit no axis deps +1.95
axis dials
+2.83 n/a +1.95
Agno Agent Frameworks
2 of 3 axes measurable
46
p25
vel -0.17 cit no axis deps -0.54
axis dials
-0.17 n/a -0.54
AutoGen Agent Frameworks
2 of 3 axes measurable
48
p31
vel +0.29 cit no axis deps -0.63
axis dials
+0.29 n/a -0.63
CAMEL Agent Frameworks
3 of 3 axes measurable
51
p38
vel -0.63 cit +0.00 deps +0.76
axis dials
-0.63 +0.00 +0.76
CrewAI Agent Frameworks
2 of 3 axes measurable
54
p50
vel -0.21 cit no axis deps +0.89
axis dials
-0.21 n/a +0.89
Google ADK Agent Frameworks
2 of 3 axes measurable
62
p81
vel +1.51 cit no axis deps +0.36
axis dials
+1.51 n/a +0.36

Full Agent Frameworks cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state
scored
Cohort z
-0.40
OLS slope
+0.017
Theil-Sen slope
+0.017
Latest direct dependents
166
Confirmed-clean points
23
Reconstructed history points
15
As-of partition
2026-09-07
Fragility veto
inactive
Rising vote
no

This axis measures the frozen-panel trajectory of the package set selected and linkage-verified as of 2026-07-21. Systems outside that panel are not measured on this axis. Residual survivorship beyond the frozen universe is disclosed, not denied.

The earliest weekly points of each series were read from deps.dev's BigQuery history on 2026-07-21; later points are weekly captures. 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_X9JA7ZTD6TF methodology m3 snapshot 9d2fe956adbc period 2026-w39 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m3, never edited by hand. Cite as: “Evidaxis, DSPy, entity e_X9JA7ZTD6TF, snapshot 2026-w39.”

Durable reference (format-independent): urn:evidaxis:claim:e_X9JA7ZTD6TF:m3:2026-09-26