Metraipolis › archive › dc_ff79776657cb
ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring — arXiv:2610.06744
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06744
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:28:40.959Z
- SHA-256 of the archived text
b15eeeffeafc9e36af08773a749038f666d2fbfed65af4b597d273e0f0a30854- Stable URL of this page
https://metraipolis.com/documento/dc_ff79776657cb
How to cite
ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring — arXiv:2610.06744 — arXiv, https://arxiv.org/abs/2610.06744 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff79776657cb (Metraipolis archive dc_ff79776657cb, sha256 b15eeeffeafc9e36af08773a749038f666d2fbfed65af4b597d273e0f0a30854)
BibTeX
@misc{dcff79776657cb,
title = {ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring — arXiv:2610.06744},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06744},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff79776657cb; sha256 b15eeeffeafc9e36af08773a749038f666d2fbfed65af4b597d273e0f0a30854},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06744. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
ufakzeka-karar is an open Turkish decision model with 182,494,466 parameters. Given a Turkish text and questions of a fixed answer type (a choice, a level on an ordered scale, or yes or no), it returns a temperature-scaled probability for every option and an expected error that serves as a "not sure" signal, without generating text and in one CPU forward pass for up to ten options. Built on the lab's ufakzeka-1-base, its head scores each option blind to the others at shared positions, so the answer does not depend on option order. A sequential head trained with shuffled options was about as accurate but changed 2.3 to 2.8 percent of its answers when only the option order changed; REINFORCE lost 10.2 points (0.102) of macro F1 to cross-entropy. On the open set of HakemBench v1.0 (4,275 questions, 7 tracks) the released model ranks 7th of 16 rows with a composite of 0.660 (95% interval 0.642 to 0.677). Temperature scaling lowers calibration error (smooth ECE) on the development set but raises it on held-out support questions, from 0.027 to 0.045 for the first scored run, which never trained on them; the released model later trained on them, so its 0.036 to 0.064 is not an unseen-question test. The released model is the last of three runs scored on HakemBench, and its numbers are not blind. The second run's new training data was aimed at the first run's errors on the full test set in guardrails, moderation and customer support, and the released run was trained after the second run's guardrail results on the full test set were read, under a protocol fixed in writing before any of its data, code or runs. All its numbers come after these readings; its guardrail, moderation and customer support numbers carry the flag "shaped by reading the test results". With every model scored on the other four tracks only, its composite is 0.678, 6th of 16. Weights and code are under Apache-2.0. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.06744 — 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 2026-10-06T05:24:20.394Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).