pith. sign in
Pith Number

pith:Y4ON2ORU

pith:2026:Y4ON2ORUSI4VKQTORTVHIX6FQH
not attested not anchored not stored refs resolved

The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance

Arto Hellas, Bita Akram, Evanfiya Logacheva, Francisco Castro, Jing Fan, Juho Leinonen, Narges Norouzi, Peter Brusilovsky, Tsvetomila Mihaylova

LLM-generated feedback is associated with faster time to solution for programming assignments than compiler messages alone.

arxiv:2605.16933 v1 · 2026-05-16 · cs.HC

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Y4ON2ORUSI4VKQTORTVHIX6FQH}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Results from an online programming course show that LLM-generated feedback is associated with faster time to solution compared to the no-feedback baseline, with less guided feedback showing slightly stronger effects.

C2weakest assumption

The study assumes that the three feedback types were implemented with meaningfully different levels of guidance and that students actually read and used the feedback rather than ignoring it or treating all conditions the same.

C3one line summary

LLM-generated feedback was associated with faster time to solution for programming students than compiler messages alone, with less-guided versions showing slightly stronger effects.

References

69 extracted · 69 resolved · 0 Pith anchors

[1] Moraes, Fernanda Oliveira, and Carla A 2025 · doi:10.1007/978-3-031-98417-4_30
[3] Craig Boyle and Antonio O. Encarnacion. 1994. Metadoc: an adaptive hypertext reading system. User Modeling and User-Adapted Interaction, 4(1):1--19 1994
[4] Breslow and David G 1993 · doi:10.2307/2290687
[5] Neil CC Brown, Pierre Weill-Tessier, Juho Leinonen, Paul Denny, and Michael K \"o lling. 2025. Howzat? appealing to expert judgement for evaluating human and ai next-step hints for novice programmers. 2025
[6] Marc Brysbaert and Micha \"e l Stevens. 2018. Power analysis and effect size in mixed effects models: A tutorial. Journal of cognition, 1(1):9 2018
Receipt and verification
First computed 2026-05-20T00:03:31.559558Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

c71cdd3a34923955426e8cea745fc581e103d51f07974c8d896d50e09453f713

Aliases

arxiv: 2605.16933 · arxiv_version: 2605.16933v1 · doi: 10.48550/arxiv.2605.16933 · pith_short_12: Y4ON2ORUSI4V · pith_short_16: Y4ON2ORUSI4VKQTO · pith_short_8: Y4ON2ORU
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Y4ON2ORUSI4VKQTORTVHIX6FQH \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: c71cdd3a34923955426e8cea745fc581e103d51f07974c8d896d50e09453f713
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "6ab9c2f15094a6f9397d9e6899210462ba1a6d201b4dcc45aa767b5e7e3755dc",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.HC",
    "submitted_at": "2026-05-16T11:02:33Z",
    "title_canon_sha256": "108c523b89a21c0734169668b3c895dab7160409ea5c912842124eaafb3f7ee2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16933",
    "kind": "arxiv",
    "version": 1
  }
}