Skip to content
#small language model Open access

The featuretree IR: an Open Feature-Tree Format, Emitted Natively into Several CAD Systems and Checked by Re-Reading

Oct 2026 · Zenodo (CERN European Organization for Nuclear Research) · 1 references
Manufacturing Process and Optimization

Abstract

When a program or a language-model agent writes a part, a person still has to be able to open it, see how it was built, and change one dimension without starting again. That needs a shared, small description of the feature tree (the "timeline" every history-based CAD system shows) that an agent can emit, each CAD system can rebuild natively, and an edit made in any of them can be read back into. Feature-based modelling has been studied since the 1980s and no complete vocabulary exists; we publish a deliberately small one and a rule for growing it. The featuretree IR is a declarative JSON list of named features (sketches with arcs, pad, pocket, fillet, revolve and placed cuts, with draft) whose references to faces and edges are stored as queries resolved against live geometry, never as kernel identifiers. One IR is emitted as a native, editable tree in FreeCAD, build123d and Onshape, and as scripts for Autodesk Fusion and SolidWorks (not yet run). Every emitted part is checked the same way: STEP export, a volume and Boolean-free IoU gate against a reference build, and a per-feature volume trace that names the first feature where two backends disagree. On the eleven trees recovered from the NIST MBE PMI corpus FreeCAD reproduces the reference on 10 of 11; Onshape, limited by its free plan's API quota, has run 3 and passes 1. An edit made in the FreeCAD tree, read back by feature name and rebuilt by the reference, agrees on 43 of 46 single-dimension edits (27 before a defect this measurement found was fixed). Of the 240 features in the designers' own trees of the same parts, 52% have a kind of their own in the IR; hole, pattern and chamfer would bring that to 94%. Running the backends against each other found six defects, including one in the reference backend and two rules the specification had never stated. Neutral feature exchange is not new, and we claim no novelty; we offer an open specification, an MIT-licensed implementation, and reproducible measurements. Version 2 adds the mapping to each system's feature tree, the edit round trip, the vocabulary coverage, the rule for adding feature kinds, and one more Onshape part. Numbers come from the repository tag ir-paper-v2.

View source

Similar papers

#small language model Dataset Open access Oct 2026

Socratic guiding questions in synthetic arithmetic data: matched LoRA runs (revision v2)

Supporting data, adapters, predictions and code for the article *Low-Cost LoRA Fine-Tuning of Small Language Models for Multi-Step Arithmetic Reasoning* by Jake O'Grady, Asena Isik Gürhan, Chee Fong Ting and Effirul Ramlan (University of Galway). We generated 20,000 GSM8K-derived arithmetic problems with step-by-step s...

O'Grady, Jake, Gürhan, Asena Isik, Chee, Fong Ting et al. · 465 citations
#computer vision Open access Jun 2016

Software Development in Startup Companies: The Greenfield Startup Model

The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.

Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al. · 178 citations · ⚡14
#computer vision Open access Oct 2016

Software Startups - A Research Agenda

Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.

M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al. · 157 citations · ⚡17
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#computer vision Open access Feb 2018

Lean Internal Startups for Software Product Innovation in Large Companies: Enablers and Inhibitors

This study investigates how Lean internal startup facilitates software product innovation in large companies and identifies its enablers and inhibitors, and shows the potential of the method-in-action framework to investigate the Lean startup approach in non-startup context.

Henry Edison, Nina M. Smørsgård, Xiaofeng Wang et al. · 78 citations · ⚡6

Related blog posts

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.