Pith Number

pith:HIOEVHIC

pith:2026:HIOEVHICW4D3AJO7WCLPMVFBOD

not attested not anchored not stored refs resolved

Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning

Jan Net\'ik, Patr\'icia Martinkov\'a

Fine-tuned transformers predict multiple-choice item difficulty directly from wording, with multi-task learning aiding small-sample cases.

arxiv:2605.16991 v1 · 2026-05-16 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{HIOEVHICW4D3AJO7WCLPMVFBOD}

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

the multi-task variant delivers significant paired improvements in the smallest-sample regime. Transformer fine-tuning, especially if regularised by a suitable auxiliary task, recovers a substantial share of the wording-derivable signal at training-set sizes typical of applied measurement.

C2weakest assumption

That difficulty is sufficiently determined by surface and inferential features in the item wording alone, independent of the specific student population or test context; this enters when the authors treat the held-out test set performance as evidence of wording-derivable signal without population-specific calibration data.

C3one line summary

Fine-tuned transformers with multi-task learning recover substantial wording-derived signal for item difficulty at small sample sizes typical in applied testing.

References

190 extracted · 190 resolved · 9 Pith anchors

[1] and Tamma, Valentina , date = · doi:10.1007/s40593-023-00362-1

[2] Belov, Dmitry and Lüdtke, Oliver and Ulitzsch, Esther , date =. A. OSF , doi =

[3] A quantitative study of

[5] arXiv , doi =

[6] 1997 , pages = · doi:10.1023/a:1007379606734

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:03:34.868769Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3a1c4a9d02b707b025dfb096f654a170f0e78f3bcc102fa70c829e0ff46fc295

Aliases

arxiv: 2605.16991 · arxiv_version: 2605.16991v1 · doi: 10.48550/arxiv.2605.16991 · pith_short_12: HIOEVHICW4D3 · pith_short_16: HIOEVHICW4D3AJO7 · pith_short_8: HIOEVHIC

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/HIOEVHICW4D3AJO7WCLPMVFBOD \
  | 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: 3a1c4a9d02b707b025dfb096f654a170f0e78f3bcc102fa70c829e0ff46fc295

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d10c676ce8323e7d68784b3a0ea0a7f1fffaabc94a48e2258174993e0971f891",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-16T13:22:57Z",
    "title_canon_sha256": "12f0ea05281bedd77611a52f9e40ab488bf728daeddb807c78d858a49e8a6325"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16991",
    "kind": "arxiv",
    "version": 1
  }
}