Lessons from 59 Linux Kernel Bug Reports
Comments on “Lessons from 59 Linux Kernel Bug Reports”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
Microsoft's FORGE Lab describes a three-month effort in which its MDASH scanner, run mainly on Sonnet 4.6 and GPT models over some kernel subsystems, yielded 26,502 raw findings. Those were narrowed to 621 cases with proof-of-concept evidence, then 59 upstream reports, 33 CVEs and 38 merged fixes. Eight CVEs have confirmed root exploits. The lab says expert triage and maintainer review took months, so human effort is the bottleneck. The figures are self-reported and could not be independently verified.
Why it ranked
No. 5 of 137 with a score of 0.72. The panel rated it highest on new information (0.93) and technical depth (0.92), lowest on significance (0.69).
- AI judgeJudge 2claude-haiku-5-5
- Detailed, well-substantiated account of AI-driven Linux kernel vulnerability discovery with a concrete root-cause walkthrough and CVEs; high security and AI relevance, with some vendor-promotional framing of the MDASH tool.
- AI judgeJudge 3gpt-5.6-luna
- Detailed primary engineering evidence covers AI-assisted Linux vulnerability discovery, exploit validation, upstream fixes, and the human bottleneck. It is highly actionable for security practitioners, technically deep, and presents substantial new findings, with only modest promotional framing.
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
0.72total under rubric v2.3
- Significance0.69
- Reader interest0.84
- Audience breadth0.71
- Practical relevance0.72
- Substantiated0.90
- Technical depth0.92
- New information0.93
- Counts against: Promotional0.16
- Counts against: Overclaim0.16
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) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.66 | 0.60 | 0.82 | 0.69 | 0.22 | +0.24 | +0.166 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.73 | 0.85 | 0.94 | 0.84 | 0.21 | +0.26 | +0.218 |
| Audience breadthHow many people who build technology does it concern? | 0.68 | 0.67 | 0.78 | 0.71 | 0.11 | +0.13 | +0.092 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.62 | 0.70 | 0.83 | 0.72 | 0.21 | +0.22 | +0.158 |
| 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. | 0.93 | 0.85 | 0.92 | 0.90 | 0.08 | +0.05 | +0.045 |
| Technical depthHow technically substantive is it? | 0.96 | 0.85 | 0.95 | 0.92 | 0.12 | +0.05 | +0.046 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.86 | 0.95 | 0.98 | 0.93 | 0.12 | +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. | 0.10 | 0.20 | 0.18 | 0.16 | 0.10 | −0.19 | −0.030 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.17 | 0.20 | 0.12 | 0.16 | 0.08 | −0.11 | −0.018 |
| Sum of contributions | +0.724 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.724 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-11-13/5/"><img src="https://rubric.hrih.si/badge/2026-11-13/5.svg" alt="Ranked #5 on Rubric, 13 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 4 no source given · 4 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
Couldn’t checkNumber
Microsoft's FORGE Lab's MDASH effort has produced 59 public upstream Linux kernel reports and 33 assigned CVEs.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “which has so far produced 59 public upstream reports and 33 assigned CVEs”
The source says No passage could be compared.
Source cited by the article: lore.kernel.org/all
No source givenNumber
The FORGE Lab team confirmed working root privilege-escalation exploits for eight of the CVEs, and fixes for 38 reports have been merged into mainline.
The article gives no link or citation for it.
The article says “We confirmed working root privilege-escalation exploits for eight of those CVEs, and fixes for 38 of our reports have been merged into mainline”
The source says No source to compare with.
No source givenNumber
The initial MDASH scans produced 26,502 raw findings in about two weeks, which were filtered to 11,769 candidates and then 621 PoC-backed cases.
The article gives no link or citation for it.
The article says “The codename MDASH scans produced 26,502 raw scan findings in about two weeks on two servers”
The source says No source to compare with.
No source givenNumber
Across the 59 reports, the average bug was 8.1 years old when first reported publicly.
The article gives no link or citation for it.
The article says “Across the 59 reports, the average bug was 8.1 years old when we first reported it publicly”
The source says No source to compare with.
Couldn’t checkNumber
The cls_u32 shift-out-of-bounds bug (CVE-2026-74544) had been in the kernel for at least 21 years.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “had been there for at least 21 years”
The source says No passage could be compared.
Source cited by the article: lore.kernel.org/all/20260720034514.23053-1-blbllhy@gmail.com
Couldn’t checkDate
The first public report went out on June 27, 2026.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “Our first public report went out on June 27, 2026”
The source says No passage could be compared.
Source cited by the article: lore.kernel.org/all/20260627024023.2201160-1-xmei5@asu.edi
No source givenNumber
Of the 33 assigned CVEs, 24 are rated High or above (CVSS v3.1 score of at least 7.0).
The article gives no link or citation for it.
The article says “24 are rated High or above (CVSS v3.1 score of at least 7.0”
The source says No source to compare with.
Couldn’t checkCausal conclusion
A 2018 commit moved the iter->p reset into rhashtable_walk_start_check() but only on one of two resume paths, causing the missed reset behind CVE-2026-64563.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “a 2018 commit (5d240a8936f6) kept iter->p across walk_stop() and moved the reset into rhashtable_walk_start_check()—but only on one of its two resume paths”
The source says No passage could be compared.
Source cited by the article: github.com/torvalds/linux/commit/5d240a8936f6a1d3ece06701e8c4d830a2eca8a8
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 1 pts, not on front page
Recorded for context only, checked 15 Nov 2026, 20:42 UTC. It played no part in the ranking.