Edition of Wednesday 11 November 2026

Introducing AlphaProof Code: a breakthrough in verifying complex software at depth

Comments on “Introducing AlphaProof Code: a breakthrough in verifying complex software at depth”

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

Google DeepMind researchers Pushmeet Kohli and Swarat Chaudhuri report that their AlphaProof Code framework, which uses AI agents to write Lean proofs, formally verified the actual compiled code of Signal's cryptographic protocol in four weeks.

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

Why it ranked

No. 71 of 143 with a score of 0.63. The panel rated it highest on new information (0.93) and significance (0.84), lowest on substantiated (0.62). Overclaim counted against it (0.59). Placed No. 71, No. 59 by score alone: the 21st Security story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Major landmark-style claim on formally verifying Signal's implementation with AI agents, backed by a technical paper and open artifacts, but company-blog framing and claims of 'first' warrant some discount on substantiation and overclaim.
AI judgeJudge 3gpt-5.6-luna
The article describes a technically consequential AI-assisted formal-verification effort with concrete scale, method, bug tests, and open artifacts. Its extraordinary “first” and time-saving claims remain largely self-reported, making promotion and overclaim probabilities substantial.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.63total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.84
  • Reader interest0.84
  • Audience breadth0.76
  • Practical relevance0.65
  • Substantiated0.62
  • Technical depth0.66
  • New information0.93
  • Counts against: Promotional0.42
  • Counts against: Overclaim0.59

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

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.920.720.900.840.20+0.24+0.203
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.690.900.940.840.25+0.26+0.219
Audience breadthHow many people who build technology does it concern?0.820.670.780.760.15+0.13+0.098
Practical relevanceHow useful is it to someone who builds software or tech products?0.630.550.780.650.23+0.22+0.144
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.580.600.680.620.10+0.05+0.031
Technical depthHow technically substantive is it?0.650.600.720.660.12+0.05+0.033
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.880.950.960.930.08+0.05+0.047
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.320.350.580.420.26−0.19−0.079
OverclaimDo the headline or conclusions claim more than the body supports?0.610.450.720.590.27−0.11−0.065
Sum of contributions+0.630
Claim-check penalty0.000
Total, as published0.630

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

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #71 on Rubric, 11 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-11/71/"><img src="https://rubric.hrih.si/badge/2026-11-11/71.svg" alt="Ranked #71 on Rubric, 11 Nov 2026" width="245" height="28"></a>

Also covered by

Elsewhere

Elsewhere: HN 605 pts, front page

Discussion on Hacker News

Recorded for context only, checked 11 Nov 2026, 05:47 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. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “Introducing AlphaProof Code: a breakthrough in verifying complex software at depth”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.