Metraipolis › archive › dc_38a7014257e4

Prism-1: Position- and Rival-Independent Scoring for System One Models — arXiv:2610.22066

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.22066
License (as archived): CC0-1.0
Archived: 2026-10-16T09:05:23.607Z
SHA-256 of the archived text: adb5400cef322af2a13c69d94c5b3de93942c3b64b6364429aaf91f46936bcc0
Stable URL of this page: https://metraipolis.com/documento/dc_38a7014257e4

How to cite

Prism-1: Position- and Rival-Independent Scoring for System One Models — arXiv:2610.22066 — arXiv (en), https://arxiv.org/abs/2610.22066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_38a7014257e4 (Metraipolis archive dc_38a7014257e4, sha256 adb5400cef322af2a13c69d94c5b3de93942c3b64b6364429aaf91f46936bcc0)

BibTeX

@misc{dc38a7014257e4,
  title = {Prism-1: Position- and Rival-Independent Scoring for System One Models — arXiv:2610.22066},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22066},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_38a7014257e4; sha256 adb5400cef322af2a13c69d94c5b3de93942c3b64b6364429aaf91f46936bcc0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in one forward pass, without generated reasoning. Web systems increasingly build them by reading decisions from language models. Two axioms of rational choice are natural requirements for such decisions, because in web systems the listing and the option set are determined by other components and can change or be manipulated: the order in which the options are listed should not matter, and adding an option should not change the relative odds of the others (Luce's choice axiom). We test the standard reads, namely single-choice question (SCQ) prompting, with shuffled-order training, order averaging or sorted options, and invariant set architectures, and find that each violates at least one axiom: one shuffle changes 12-20% of SCQ answers, sorting only freezes an arbitrary convention, and a well-chosen added option steers 4-34% of decisions. By Luce's theorem, a read satisfies both axioms only if it is a softmax over scores that each depend on one option alone, so in a transformer they hold by construction only if no token that scores an option sees another. We implement this as Prism-1 (Position- and Rival-Independent Scoring for System One Models): every option is read in its own block at shared positions, with the model's usual left-to-right attention, in one forward pass. On five benchmark sets with Qwen3-8B and Gemma 4 12B, SCQ prompting trained on the same data still changes 7% of its answers under one shuffle, and an added irrelevant option steers 12% of its decisions. Prism-1 stays within one point of that baseline's accuracy and is 2-4 points more accurate once only answers that survive a reordering are counted, while no shuffle changes any of its answers and no added irrelevant option moves its choice among the others.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22066 — 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 2026-10-16T08:44:17.808Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).