SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

No. 98 of 245 · arXiv · Arnon Mazza, Elad Levi · published 23 Oct 2026, 04:00 UTC · 50 min read

AI & machine learning
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

SCOPE compiles a natural-language policy into an executable neurosymbolic program that composes outputs from small neural predicates, deterministic extractors, and code, then refines both the program and its training data through adversarially generated counterexamples.

Read the original at arxiv.org. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.66total under rubric v2.0

Significance0.62
Reader interest0.73
Audience breadth0.58
Practical relevance0.73
Substantiated0.81
Technical depth0.89
New information0.89
Counts against: Promotional0.08
Counts against: Overclaim0.36

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.68	0.40	0.78	0.62	0.38	+0.25	+0.155
Reader interest	0.68	0.60	0.92	0.73	0.32	+0.20	+0.147
Audience breadth	0.57	0.45	0.72	0.58	0.27	+0.10	+0.058
Practical relevance	0.76	0.60	0.82	0.73	0.22	+0.15	+0.109
Substantiated	0.95	0.70	0.78	0.81	0.25	+0.10	+0.081
Technical depth	0.91	0.80	0.96	0.89	0.16	+0.10	+0.089
New information	0.87	0.80	0.99	0.89	0.19	+0.10	+0.089
Promotional	0.07	0.10	0.08	0.08	0.03	−0.15	−0.012
Overclaim	0.39	0.35	0.35	0.36	0.04	−0.15	−0.054
Sum of contributions							+0.660
Claim-check penalty							0.000
Total, as published							0.660

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.