Academic Ancestry is an academic family tree for everyone: who supervised whom, up and down the generations, with the examiners, coauthors and teachers beside them, built only from open sources. What sets it apart is that every link says where it came from, and where the record stops, the page says so.
An academic family: who supervised whom, up and down the generations, with examiners, coauthors and teachers beside them. It is built only from open sources, keeps the theses and works it finds as an index of authorship, and says plainly where its knowledge stops. It is not a ranking, and it does not guess.
The record is a graph. Its things are people, theses and other works; its links are roles a record gives a person on a thesis or a work. Supervision makes the lineage; examining, sitting on a committee or opposing a defence sit beside it; coauthorship, citation and teaching are drawn and never counted as lineage.
Every link in the record carries the kind of evidence behind it: cited by a repository's record, stated by Wikidata, found in a thesis's own text, inferred from a convention or from shared papers, or claimed by the person on their ORCID record. The kinds are never merged, and only some are counted. Each cited link can be traced to the record it rests on and the day it was read, and where the sources stop, the page says so.
Theses come from university repositories, national registers and the shared repositories of many universities; who supervised whom comes from their records and from Wikidata. Papers and coauthors are asked of OpenAlex, and a person's own list of works of ORCID, as a page opens. Every source is read openly, under the site's own name, at the pace its host asks.
Every night each source is asked for what has changed, its records are read into theses, the people in them are told apart, their roles become links, and the whole source is replaced in the record at once. Repositories describe theses in many dialects, so each format has one reader, and each source's own habits are met by small rules declared beside it. A change in how a source is read reaches the record only once it has been compared with the reading before and the difference declared.
A name is not a person. Within one repository a spelling stands for one person; across sources, two entries are joined only where their records share an identifier such as an ORCID iD, or where the join was checked on a sample read by a person, and never on a shared name alone. A match a person confirmed is shown apart from one that is only likely.
A way of reading a source is not taken on its writer's word. It is checked: a sample of what it read is compared with what the source itself shows, such as the thesis's own page or title page, and it passes where 0.90 of the sample or more agree. Every check is listed here as it was measured, the failures among them, and every count the site shows comes from a reading of the record, dated by the day it was made.
The record is made without a language model: its links come from the sources' own records, read by written rules. Anthropic's Claude is used in bounded places beside it: the assistant that answers questions about the sheet in front of you, the reading of a supervisor from a thesis's own text, a few likely teachers read with its help, and the search for leads above the top of a line. What a model reads is kept as a kind of its own, comes in through a check, or stays outside as a lead that is never drawn.
An AI assistant such as Claude can ask the record for you through the Model Context Protocol, an open standard for giving an assistant tools. The site's tools find people, walk lineages, trace the routes between people and say where the record stops, and one reports a missing advisor or work. Every call is made under your own account and passes the same rules as a page: a person who asked not to be shown is never answered.
Every person's page and thesis page has a twin a program can read, in schema.org's shared vocabulary, and a citation to copy. Search engines are offered the pages of people with students and of theses that name a supervisor. The record as a whole is to be released as data under CC0, free for any use.
A source is first read on a short-lived Amazon EC2 machine, and every raw record is kept in Amazon S3. One server holds the record in PostgreSQL, answers in Python and draws the pages with React on Node, behind Amazon CloudFront. Every night it reads each source again, many hosts side by side and the heavy work one source at a time.
The record holds what its sources hold. Many theses name no supervisor, many state no level, one person spelled two ways stays two until an identifier joins them, and some countries are barely reached. Each gap is shown where it falls, with the reason where the record knows it, and never filled by a guess.
The words the site uses, from cited and stated to sameAs and CC0, each in a sentence or two. Every term links to the page that explains it in full.
The privacy notice says what the site shows about the people it names, what it keeps of its readers, and how a person asks not to be shown. To add what the record lacks, report a missing advisor or a missing work; to point to a repository it does not read, or for anything else, write to academicancestry@proton.me.