Designing for Semi-Formal Programming with Foundation Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
End-user programmers, such as scientists and data analysts, communicate their intent through culturally specific, semi-formal representations like formulas and wireframes. Research on end-user programming interfaces has sought to democratize programming but has required advances in program synthesis, UI design, and computer vision to support translating a representation to code. As a result, end-users must still frequently translate such representations manually. Foundation models like ChatGPT and GPT-4V dramatically lower the cost of designing new programming interfaces by offering much better code synthesis, UI generation, and visual comprehension tools. These advances enable new end-user workflows with more ubiquitous semi-formal representations. We outline the translation work programmers typically perform when translating representations into code, how foundation models help address this problem, and emerging challenges of using foundation models for programming. We posit semi-formal and notational programming as paradigmatic solutions to integrating foundation models into programming practice. Articulating a design space of semi-formal representations, we ask how we could design new semi-formal programming environments enabled through foundation models that address their emergent challenges, and sketch “proactive disambiguation” as one solution to bridging gulfs of evaluation and execution.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it