Every Mac comes with an (undocumented) family member classifier
Comments on “Every Mac comes with an (undocumented) family member classifier”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
Eighth Rank reports that macOS 26 runs two daemons, knowledgeconstructiond and intelligenceplatformd, that build an on-device knowledge graph from Contacts, Calendar, Photos, Family Sharing, communication logs and location. It is stored in plaintext SQLite under Full Disk Access protection, with 181 entity classes and 278 predicates, including inferred family relationships. The man page is nearly the only Apple documentation, and the mechanism mapping is the authors' inference. Most specific figures, including the family classifier details, lack independent sourcing. Developers should note the privacy exposure if that store is compromised.
Why it ranked
No. 11 of 51 with a score of 0.68. The panel rated it highest on technical depth (0.92) and reader interest (0.85), lowest on audience breadth (0.63). Placed No. 11, No. 7 by score alone: the fifth Security story of the day (−0.040). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Detailed reverse-engineering of an undocumented macOS on-device knowledge graph with specifics, open-source tool, and privacy/security implications; strong technical depth, though some claims remain inference and the threat section is speculative.
- AI judgeJudge 3gpt-5.6-luna
- Detailed reverse engineering of macOS’s personal knowledge graph, its data sources, inference mechanisms, storage, and an open-source inspection tool. Strong evidence and technical depth, with some cautiously framed inferences and mildly sensational 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
0.68total under rubric v2.3
- Significance0.68
- Reader interest0.85
- Audience breadth0.63
- Practical relevance0.65
- Substantiated0.85
- Technical depth0.92
- New information0.82
- Counts against: Promotional0.07
- Counts against: Overclaim0.38
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? | 0.60 | 0.60 | 0.84 | 0.68 | 0.24 | +0.24 | +0.164 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.74 | 0.85 | 0.95 | 0.85 | 0.21 | +0.26 | +0.220 |
| Audience breadthHow many people who build technology does it concern? | 0.48 | 0.60 | 0.80 | 0.63 | 0.32 | +0.13 | +0.081 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.61 | 0.50 | 0.82 | 0.65 | 0.32 | +0.22 | +0.142 |
| 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. | 0.94 | 0.70 | 0.90 | 0.85 | 0.24 | +0.05 | +0.042 |
| Technical depthHow technically substantive is it? | 0.97 | 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)? | 0.92 | 0.60 | 0.94 | 0.82 | 0.34 | +0.05 | +0.041 |
| 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. | 0.06 | 0.10 | 0.04 | 0.07 | 0.06 | −0.19 | −0.013 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.55 | 0.30 | 0.30 | 0.38 | 0.25 | −0.11 | −0.042 |
| Sum of contributions | +0.682 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.682 | ||||||
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/2026-11-08/11/"><img src="https://rubric.hrih.si/badge/2026-11-08/11.svg" alt="Ranked #11 on Rubric, 8 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 1 matches source · 6 no source given · 1 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
No source givenGeneralization
Every Mac since 2022 ships a pair of daemons whose purpose is to build a graph about the user and the people around them.
The article gives no link or citation for it.
The article says “every Mac since 2022 ships a pair of daemons whose only purpose in life is to build a graph about you and the people around you”
The source says No source to compare with.
Matches sourceDate
Apple's own researchers published a paper in 2023 on the techniques behind this graph construction.
The cited source says the same thing.
The article says “Apple's own researchers did publish a paper on the techniques behind this graph construction, back in 2023”
The source says “USACompanion of the 2023 International Conference on Management of Data (SIGMOD-Companion ’23), June 18–23, 2023, Seattle, WA, USAPrice”
Source cited by the article: arxiv.org/abs/2305.09464
No source givenDate
Nic Lydon came across the same database a few months earlier and wrote it up in a post titled 'I Built a Personal Knowledge Graph. Apple Had Already Built One on My Laptop.'
The article gives no link or citation for it.
The article says “Nic Lydon came across the same database and wrote it up in I Built a Personal Knowledge Graph. Apple Had Already Built One on My Laptop”
The source says No source to compare with.
Couldn’t checkDate
In September 2026, Alexis Brignoni taught iLEAPP to read the same store on iOS, where graph.db and ontology.db sit under /private/var/mobile/Library/IntelligencePlatform.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “in September 2026, Alexis Brignoni taught iLEAPP to read the same store on iOS”
The source says No passage could be compared.
Source cited by the article: github.com/abrignoni/iLEAPP
No source givenNumber
graph.db is a triple store written in a vocabulary of 181 entity classes and 278 predicates.
The article gives no link or citation for it.
The article says “It is a triple store written in a vocabulary of 181 entity classes and 278 predicates”
The source says No source to compare with.
No source givenNumber
A pair of XGBoost classifiers decides who is family from 144 mostly behavioral features.
The article gives no link or citation for it.
The article says “a pair of XGBoost classifiers decides who is family from 144 mostly behavioral features”
The source says No source to compare with.
No source givenNumber
The face co-occurrence graph covers 8,904 clustered faces over the 1,643 photographs that hold more than one face.
The article gives no link or citation for it.
The article says “8,904 clustered faces over the 1,643 photographs that hold more than one”
The source says No source to compare with.
No source givenDate
macOS 27 was released on September 14, 2026, and after upgrading to 27.0.1 the graph withdrew most of the rows built from Contacts, Calendar, Siri Suggestions, Family Sharing and the app catalog, then rebuilt them over the following day.
The article gives no link or citation for it.
The article says “macOS 27 was released on September 14, 2026. After the upgrade to 27.0.1, the graph withdrew most of the rows it had built”
The source says No source to compare with.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 662 pts, front page
Recorded for context only, checked 8 Nov 2026, 05:46 UTC. It played no part in the ranking.