Metraipolis › archive › dc_7bdd5d2b090b

Prediction Is Not Calibration: Item Parameter Recovery and Representation Coupling in Knowledge Tracing — arXiv:2610.30211

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30211
License (as archived)
CC0-1.0
Archived
2026-10-23T15:14:46.631Z
SHA-256 of the archived text
987a1927b193ea5361958cee1d2389a6246517161c1bcd78b59a9ad432702d24
Stable URL of this page
https://metraipolis.com/documento/dc_7bdd5d2b090b

How to cite

Prediction Is Not Calibration: Item Parameter Recovery and Representation Coupling in Knowledge Tracing — arXiv:2610.30211 — arXiv (en), https://arxiv.org/abs/2610.30211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bdd5d2b090b (Metraipolis archive dc_7bdd5d2b090b, sha256 987a1927b193ea5361958cee1d2389a6246517161c1bcd78b59a9ad432702d24)
BibTeX
@misc{dc7bdd5d2b090b,
  title = {Prediction Is Not Calibration: Item Parameter Recovery and Representation Coupling in Knowledge Tracing — arXiv:2610.30211},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30211},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bdd5d2b090b; sha256 987a1927b193ea5361958cee1d2389a6246517161c1bcd78b59a9ad432702d24},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge tracing (KT) models can estimate item parameters through an item response decoder trained solely for next-response prediction, yet predictive accuracy does not guarantee parameter recovery. We study 2PL, GPCM, and NRM decoders paired with LSTM, Transformer, and DKVMN encoders. Response-model derivatives show why discrimination and option slope updates depend directly on the scale and spread of estimated ability. Affine logit identities show how item-dependent shifts and rescaling in estimated ability are absorbed into item parameters without changing response probabilities. In simulations, difficulty, mean threshold, and correct-option intercept recovery remain high under shuffled order across representation widths, whereas discrimination and keyed option slope contrast recovery require wider item representations and degrade further under fixed item order. Separating the sequence item representation (width $d_S$) from the item parameter key (width $d_M$), and pairing a wide key with a thin sequence representation ($\mathrm{SK}(64,8)$), reduces fixed-order ability distortions and improves recovery and cross-order consistency without sacrificing test accuracy or increasing model size relative to a shared width-64 baseline ($\mathrm{SH}(64)$). On TIMSS and EdNet, widening $d_M$ consistently improves agreement with an offline IRT reference, while the trade-off from narrowing $d_S$ depends on the encoder's reliance on sequence width for prediction. These findings show why item parameters, especially discrimination and option slopes, must be evaluated separately from response prediction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30211 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-23T15:09:08.496Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).