Jev directory
CommunityJev Models & Reimplementations
ROR Set Point Retriever E5 Base (OpenAlex Jev Distill)
A sentence-transformers retriever for ROR set point matching, distilled from OpenAlex's Jev judgments. It returns candidate ROR records for an affiliation string and is fine-tuned from intfloat/multilingual-e5-base under an MIT license.
- Reading time
- 1 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Sentence-similarity retriever built on intfloat/multilingual-e5-base.
- Distilled from the teacher judgments of openalex-affiliation-matcher v3.0.0.
- Those teacher judgments come from Jev, TypeSafe AI's closed commercial decision model.
- Finds candidate ROR records for a given affiliation string.
- MIT licensed, 278M parameters stored in a single F16 safetensors file.
Questions about this entry
Short answers drawn from the linked project or page.
It is a retriever for ROR set point matching. Given an affiliation string, it finds candidate ROR records, learning from the teacher judgments of openalex-affiliation-matcher v3.0.0.
Use sentence-transformers: from sentence_transformers import SentenceTransformer; model = SentenceTransformer("adambuttrick/ror-set-point-retriever-e5-base-openalex-jev-distill"). The card also links Google Colab and Kaggle notebooks.
It is a fine-tune of intfloat/multilingual-e5-base, an xlm-roberta based multilingual embedding model, and is tagged as a sentence-similarity pipeline.
Its labels are the teacher judgments of openalex-affiliation-matcher v3.0.0. According to the model card, those judgments come from Jev, a closed commercial decision model from TypeSafe AI.
The repository is MIT licensed. The safetensors weights total 278,043,648 parameters in F16, about 556 MB, in a single unsharded file.
The card references adambuttrick/ror-set-point-matching-train-validation-test and adambuttrick/ror-set-point-matching-train-validation-test-openalex-jev-distill as its training and validation data.
It is a retriever that surfaces candidate ROR records for an affiliation string rather than a final per-candidate decision. If you need a probability that a specific candidate is the right one, use the companion set model instead.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsMore Jev resources like this
Open Jev-style decision model built on LiquidAI's LFM2.5-350M backbone, a clone of kev. Serves the System One API contract so the TypeSafe SDK works against a local server, returning probabilities for typed questions from one forward pass.
Jev Models & Reimplementations#open-models#python#local
Communityfranckverrot/lev
An independent, from-scratch reconstruction of a Jev-style decision model that never generates text: a state plus typed questions returns a probability for every option. Trained on Qwen3-0.6B and 1.7B backbones with LoRA and served through a system_one-shaped API.
Jev Models & Reimplementations#open-models#python#research
CommunityES7/JEV-from-Scratch
A native MLX runtime for Laya's open typed-decision weights: short decisions on Apple Silicon, with no generated tokens, PyTorch, or cloud API.
Jev Models & Reimplementations#community#python#open-models
Community
mizorewww/laya-mlxPython
mizorewww/laya-mlxPythonAn open-model semantic-if engine positioned as a local Jev-style decision stack, separate from the original SemIf repo but sharing the same author.
Jev Models & Reimplementations#community#python#open-models
Community
TheoLeeCJ/SemIf-OpenJevPython
TheoLeeCJ/SemIf-OpenJevPythonLaya typed decisions through Apple Core ML and the Neural Engine, with the author's speed and energy benchmarks for short decisions on an M3 Max.
Jev Models & Reimplementations#community#python#open-models
Communitymizorewww/laya-coremlPython
mizorewww/laya-coremlPythonA local yes/no decision model that speaks Jev's wire format on a laptop CPU, refusing Choice and Score until those question types ship.
Jev Models & Reimplementations#community#python#open-models
Community
feder-cr/jevC++
feder-cr/jevC++From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.