Pith Number

pith:7KBVAEJN

pith:2026:7KBVAEJNBQFDYA6F3N6HRSIZQH

not attested not anchored not stored refs resolved

Building AI Companions that Prioritise Learning over Performance

Dragan Gasevic, Hassan Khosravi, Jason Lodge, Jason Tangen, Kristen DiCerbo, Lixiang Yan, Paul Denny, Ryan S. Baker, Shazia Sadiq, Simon Buckingham Shum

AI in education must move from performance-boosting LLMs to deliberately designed learning companions that prioritize durable understanding.

arxiv:2605.04816 v2 · 2026-05-06 · cs.HC

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7KBVAEJNBQFDYA6F3N6HRSIZQH}

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

There is a necessary shift away from LLMs designed for task-oriented performance, and beyond simply prompting them to act as tutors, toward deliberately developed AI learning companions that are pedagogically sound, adapt to their learners, and foster durable understanding, metacognitive growth, and learner agency.

C2weakest assumption

That integrating the proposed pedagogical, adaptive, and responsible design foundations into LLM-powered agents will effectively resolve the learning-performance paradox and produce measurable improvements in cognitive growth and knowledge transfer in real educational settings.

C3one line summary

Introduces AI learning companions as pedagogically informed LLM agents and proposes a three-foundation framework (pedagogical, adaptive, responsible) illustrated by five case studies to prioritize learning over performance.

References

119 extracted · 119 resolved · 0 Pith anchors

[1] G. Abdelrahman, Q. Wang, and B. Nunes. Knowledge tracing: A survey.ACM Computing Surveys, 55(11):1–37, 2023. 26 Building AI Companions that Prioritise Learning over Performance 2023

[2] S. Abdi, H. Khosravi, S. Sadiq, and D. Gasevic. Complementing educational recommender systems with open learner models. InProceedings of the tenth international conference on learning analytics & know 2020

[3] V . Aleven, B. McLaren, I. Roll, and K. Koedinger. Toward tutoring help seeking: Applying cognitive modeling to meta-cognitive skills. InInternational conference on intelligent tutoring systems, pages 2004

[4] V . Aleven, E. A. McLaughlin, R. A. Glenn, and K. R. Koedinger. Instruction based on adaptive learning technologies. InHandbook of Research on Learning and Instruction, pages 522–560. Routledge, New Y 2016

[5] J. R. Anderson, A. T. Corbett, K. R. Koedinger, and R. Pelletier. Cognitive tutors: Lessons learned.The journal of the learning sciences, 4(2):167–207, 1995 1995

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:40.796914Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fa8350112d0c0a3c03c5db7c78c91981e03e7c431178b7fbd04add3f906dbd31

Aliases

arxiv: 2605.04816 · arxiv_version: 2605.04816v2 · doi: 10.48550/arxiv.2605.04816 · pith_short_12: 7KBVAEJNBQFD · pith_short_16: 7KBVAEJNBQFDYA6F · pith_short_8: 7KBVAEJN

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/7KBVAEJNBQFDYA6F3N6HRSIZQH \
  | 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: fa8350112d0c0a3c03c5db7c78c91981e03e7c431178b7fbd04add3f906dbd31

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e1999b1f67328caf2ad970f269bd930a0146f65bbb25869b0853cbacccbf84dc",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.HC",
    "submitted_at": "2026-05-06T12:04:26Z",
    "title_canon_sha256": "bc8055e0c5f381e9f3128640720132156fd84649f4808af6cd9aaa5aafe52802"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.04816",
    "kind": "arxiv",
    "version": 2
  }
}