CodePulse-Py: an early LLM-assisted programming-education research process

Early research repository for studying LLM-assisted Python misconception detection, documenting reconstruction of student code states from keystroke logs; its app services are explicitly stubs.

Workflow level n/a Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-17 (UTC)

Primary README and repository data/replay guides. Capability/process documentation only; reported replay results deliberately omitted.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (3)

Research applicability

Offers a concrete data-preparation and evaluation-planning starting point for programming-education research; not evidence of pedagogical effectiveness.

Getting started

Editorial suggestion, not tested: read the README, data card and replay-method limitations; obtain permitted datasets and trial offline reconstruction in a controlled workspace before attempting the proposed detection/intervention study.

Maintenance

Documentation retrieved on recorded access dates; maintenance reliability not assessed.

License

No independent license/dependency or rights audit. Check repository terms and rights to source data before reuse.

Workflow & human oversight

Resource-level automation left unspecified. Researchers/educators choose materials, govern model access and verify interpretations and outputs.

Workflow level is not an evidence score; higher is not better evidence.

Approach

The data card describes student-level training/validation/replay splits and cross-cohort testing. Replay documentation explains rebuilding code from edit logs and exporting snapshots for subsequent analysis. The LLM/AST intervention remains a stated research direction, not a demonstrated tutor.

Limitations

Primary README plus data/replay documentation only; no code audit or execution. The README explicitly says application services are health-check stubs: this listing is an early research process/prototype, not a functioning adaptive tutor or verified fine-tuned model. Replay checks cover syntax, not exact code recovery. Source datasets are external, have coverage gaps and may retain identifying keystrokes; use their actual terms and protect students. No misconception accuracy, intervention benefit or reported replay performance endorsed.

Reproducibility

Primary-source documentation/excerpt review only. No installation, tests, model training, deployment or outcome reproduction.

Adoption requirements

Python 3.11, documented dependencies and separately obtained Edwards CS1 keystroke releases. Respect dataset access/usage terms and residual personal-data risks. Docker/Compose instructions launch documented stub services, not a finished product.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.