Evidaxis

SaProt

repo
AI Drug Discovery · n = 19 · westlake-repl/SaProt
Watch · conf medium
momentum
momentum 45.3 of 100 45.3 /100
momentum
45.3/100
pctile
p17
convergence gate
Convergence gate: citation passes, gate shut ×
gate
1 of 2 axes

citation passes, gate shut.

one axis passes
position in cohort distribution one of 19 in cohort
percentile 17 within cohort p25 p50 p75 p0 p100
percentile
p17
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z-1.85 within cohort, log-slope -0.004/wk.0-1.85
velocity z
-1.85 σ
slope
-0.004/wk
log-slope -0.004/wk
convergence planefull gate = rising
SaProt on the convergence plane SaProt at velocity z -1.85 and citation z +1.10, against 13 dual-axis cohort peers. citation passes gate, the other does not. z>=1 median velocity z → citation z ↑ AlphaFold3: velocity z -0.56, citation z +0.42 Boltz: velocity z -2.58, citation z +2.07 DeepChem: velocity z +2.96, citation z -0.73 DiffDock: velocity z +0.01, citation z -0.35 ESM / ESMFold: velocity z -0.03, citation z +0.49 Foldseek: velocity z -2.99, citation z +0.66 gnina: velocity z +2.86, citation z -0.35 Graphormer: velocity z +0.99, citation z -0.23 OpenFold: velocity z -0.02, citation z -0.41 ProteinMPNN: velocity z +0.00, citation z -0.51 RFdiffusion: velocity z +0.66, citation z +0.09 TorchDrug: velocity z +0.01, citation z -0.18 Uni-Mol: velocity z +0.01, citation z +0.54 SaProt
velocity z
-1.85
citation z
+1.10
peers
18

citation passes gate, the other does not.

citation z
citation z gaugecitation z+1.10 within cohort, log-slope +1.386/yr.0+1.10
citation z
+1.10 σ
slope
+1.386/yr
log-slope +1.386/yr
cohort
19
systems measured
weekly commits
0
not rising
total citations
249
present
momentum
45.3
percentile p17
commit heatmap, last 26 weeks0/wk
weekly commits, 26 weeks26 weeks of commits, peak 1 in a week, 1 active weeks, 1 total.week 1: 0 commitsweek 2: 0 commitsweek 3: 0 commitsweek 4: 0 commitsweek 5: 1 commitsweek 6: 0 commitsweek 7: 0 commitsweek 8: 0 commitsweek 9: 0 commitsweek 10: 0 commitsweek 11: 0 commitsweek 12: 0 commitsweek 13: 0 commitsweek 14: 0 commitsweek 15: 0 commitsweek 16: 0 commitsweek 17: 0 commitsweek 18: 0 commitsweek 19: 0 commitsweek 20: 0 commitsweek 21: 0 commitsweek 22: 0 commitsweek 23: 0 commitsweek 24: 0 commitsweek 25: 0 commitsweek 26: 0 commits
weeks
26
peak/wk
1
active
1
total
1
citations by yeartotal 249
Citations by year2023: 6, 2024: 62, 2025: 111, 2026: 70. Total 249 citations.2023: 6 citations2362024: 62 citations24622025: 111 citations251112026: 70 citations2670
total cites
249
years
4
latest yr
70

SaProt holds an Evidaxis momentum score of 45.3 of 100 on methodology m2, snapshot 2026-08-08, measured within the AI Drug Discovery cohort (n = 19). Its citation-momentum axis is rising within the cohort while a second independent axis has not converged, 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 +0.00, regime decelerating. prior slope -0.014, recent slope +0.000 per week. -0.014prior 39w+0.000recent 13w+0.00×
swing
+0.00×
regime
decelerating
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit Sharpereserved: <26 non-zero commit weeks
commit changepoint52 weekly commit points. Changepoint at week 4 (2025-09-06), slope change +4.494 commits per week.2025-09-06
date
week
4 of 52
Δslope
+4.494/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
4
shipped
2
reserved
4

shipped

  • recency-swing
  • commit-changepoint

reserved

  • commit-sharpe
  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m2

Verdict

SaProt is rising on citation momentum, but a second independent axis has not yet converged. It is on watch.

Path to Rising: needs development velocity to recover (at least 5 commits per week and a positive within-cohort slope).

Sources

westlake-repl/SaProt development-velocity axis
OpenAlex paper citation-momentum axis

Embed this badge

Evidaxis watch, SaProt
[![Evidaxis: SaProt](https://evidaxis.org/badge/e_9XES4XNNQCV/2026-w32.svg)](https://evidaxis.org/e/e_9XES4XNNQCV)

Others in AI Drug Discovery

AlphaFold3 AI Drug Discovery
Calibration
49
p50
vel -0.56 cit +0.42
axis dials
-0.56 +0.42
BioEmu AI Drug Discovery
Single-axis
88
p100
vel +3.02 cit no axis
axis dials
+3.02 n/a
Boltz AI Drug Discovery
Watch
47
p22
vel -2.58 cit +2.07
axis dials
-2.58 +2.07
Chai-1 AI Drug Discovery
Single-axis
30
p6
vel -1.62 cit no axis
axis dials
-1.62 n/a
DeepChem AI Drug Discovery
Tracked
64
p89
vel +2.96 cit -0.73
axis dials
+2.96 -0.73
DiffDock AI Drug Discovery
Tracked
48
p39
vel +0.01 cit -0.35
axis dials
+0.01 -0.35

Full AI Drug Discovery cohort →

entity_id e_9XES4XNNQCV 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, SaProt, entity e_9XES4XNNQCV, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_9XES4XNNQCV:m2:2026-08-08