Model card: OpenJev names in the text; note the paper's earlier name

README.md

@@ -24,9 +24,9 @@ datasets:
 
 **Jun Huang\*, Xin Ren\*** · University of Electronic Science and Technology of China · \*Equal contribution
 
-**OpenJev** (project *wev*) is an open-source, local alternative to Jev's System One decision API: same request shape, your own GPU, no API key.
+**OpenJev** is an open-source, local alternative to Jev's System One decision API: same request shape, your own GPU, no API key.
 
-**A local decision model: typed questions in, calibrated probabilities out, in one forward pass.** `wev-1.7b` answers
+**A local decision model: typed questions in, calibrated probabilities out, in one forward pass.** OpenJev-1.7B answers
 the `POST /v1/systemone` request shape (choice, yes/no and score questions over a free-form state), for general
 decisions and for browser-agent steps (*which operation? which element?*). It runs on your own GPU: no API key,
 no per-call cost, nothing generated.
@@ -64,21 +64,21 @@ wev serve --model alanhuangya/OpenJev-1.7B --port 8009   # drop-in POST /v1/syst
 ## Results
 
 Test splits, held out from training; every other model was run on the same requests and scored the same way
-(per-question accuracy; `scripts/compare.py`). For wev-4b and wev-8b, two candidates each were read on test (see the
+(per-question accuracy; `scripts/compare.py`). For OpenJev-4B and OpenJev-8B, two candidates each were read on test (see the
 repository README).
 
 **General typed decisions**
 
 | model | kev decision-v7 | kev transfer-v4 | typed-decisions |
 |---|---|---|---|
-| **wev-1.7b** | 81.1 | 65.5 | **79.5** |
+| **OpenJev-1.7B** | 81.1 | 65.5 | **79.5** |
 | Kev-4B | **88.2** | **82.1** | 65.1 |
 | Kev-8B | 88.1 | 76.8 | 62.7 |
 | Laya (typed-decisions) | 65.7 | 62.8 | 76.8 |
 | Laya | 64.3 | 63.7 | 36.2 |
 
-`wev-1.7b` trains on 80% of the typed-decisions train split, like the Laya (typed-decisions) specialist; Kev and Laya
-do not, so on that column they are generalists. kev decision-v7 is Kev's own training suite (`wev-1.7b` also trains on
+OpenJev-1.7B trains on 80% of the typed-decisions train split, like the Laya (typed-decisions) specialist; Kev and Laya
+do not, so on that column they are generalists. kev decision-v7 is Kev's own training suite (OpenJev-1.7B also trains on
 its train split); transfer-v4 is out-of-domain for every model here.
 
 **Browser steps** (Mind2Web test split: websites unseen in training, jev-ultrafast request format; step success =
@@ -86,13 +86,13 @@ operation and target element both right)
 
 | model | step success | operation |
 |---|---|---|
-| **wev-1.7b** | **68.2** | **88.1** |
+| **OpenJev-1.7B** | **68.2** | **88.1** |
 | Kev-4B | 21.2 | 35.7 |
 | Kev-8B | 19.0 | 73.3 |
 | Laya (typed-decisions) | 0.7 | 13.1 |
 | Laya | 0.0 | 2.5 |
 
-873 requests; 11 exceed the context `wev-1.7b` is evaluated with and count as wrong for it.
+873 requests; 11 exceed the context OpenJev-1.7B is evaluated with and count as wrong for it.
 
 NNetNav test split (live-web steps, DONE judged by an LLM): step success 61.0, DONE recall
 80.4, premature DONE 9.4.
@@ -136,7 +136,8 @@ check those terms before any commercial use.
 
 ## Citation
 
-Jun Huang and Xin Ren contributed equally (University of Electronic Science and Technology of China).
+Jun Huang and Xin Ren contributed equally (University of Electronic Science and Technology of China). The paper
+describes OpenJev under its earlier name, wev.
 
 ```bibtex
 @misc{huang2026wev,