Edition of Saturday 14 November 2026

Doc-foundry – AI writes Security detection rules, then proves they work

Comments on “Doc-foundry – AI writes Security detection rules, then proves they work”

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

Doc-foundry is an open-source pipeline that turns a threat (a CVE, CISA KEV entry, incident writeup, or ATT&CK technique) into a first-version Sigma detection rule, plus a proof bundle: a positive corpus, a benign baseline, an adversarial mutation set, FP/FN numbers, a coverage label, and a reproducibility hash.

Read the original at github.com. 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. 107 of 123 with a score of 0.56. The panel rated it highest on new information (0.92) and technical depth (0.86), lowest on audience breadth (0.42). The judges disagreed most on substantiated (spread 0.43), so the story is marked contested. Placed No. 107, No. 104 by score alone: the 25th 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
Tool announcement for AI-generated Sigma detection rules with a proof bundle; relevant to security builders with real technical detail, but a single project with modest breadth and claims partly unverified.
AI judgeJudge 3gpt-5.6-luna
A technically detailed security project combines LLM-authored Sigma rules with deterministic evaluation, adversarial testing, reproducibility, and human-gated deployment. It is highly actionable and novel, though evidence is presented as project claims rather than independently verified results.

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

0.56total under rubric v2.3Contestedjudges differ by 0.43 on substantiated

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.51
  • Reader interest0.72
  • Audience breadth0.42
  • Practical relevance0.71
  • Substantiated0.71
  • Technical depth0.86
  • New information0.92
  • Counts against: Promotional0.26
  • Counts against: Overclaim0.28

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?0.570.400.550.510.17+0.24+0.122
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.760.600.800.720.20+0.26+0.187
Audience breadthHow many people who build technology does it concern?0.460.400.400.420.06+0.13+0.055
Practical relevanceHow useful is it to someone who builds software or tech products?0.770.600.750.710.17+0.22+0.156
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.0.930.500.700.710.43 , above the contested threshold+0.05+0.036
Technical depthHow technically substantive is it?0.980.700.900.860.28+0.05+0.043
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.900.900.950.920.05+0.05+0.046
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.0.120.300.350.260.23−0.19−0.049
OverclaimDo the headline or conclusions claim more than the body supports?0.230.400.200.280.20−0.11−0.030
Sum of contributions+0.565
Claim-check penalty0.000
Total, as published0.565

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 #107 on Rubric, 14 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-14/107/"><img src="https://rubric.hrih.si/badge/2026-11-14/107.svg" alt="Ranked #107 on Rubric, 14 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 7 pts, front page

Discussion on Hacker News

Recorded for context only, checked 15 Nov 2026, 20:44 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 “Doc-foundry – AI writes Security detection rules, then proves they work”

More on Rubric

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