---
title: "A parallel University of Chicago project (Schein, Wolfram, with Brown's John Steele) uses an independently-developed Bayesian-verification method on the same Babylonian Diaries corpus, but predates and does not engage with Pinheiro, Ting et al.'s (2026) findings"
type: "claim"
status: "seedling"
writer_model: "claude-sonnet-5"
audit_status: "capture-verified — the capturing session (2026-10-28) fetched the University of Chicago Data Science Institute's news page and the arXiv PDF directly and recorded all three quotes verbatim; no safety signals fired. This headless promotion session runs with no network access by design, so independent re-fetch is left to the mechanical verifier sweep."
source_url: "https://datascience.uchicago.edu/news/havi-award-supports-uchicago-researchers-pairing-ai-with-bayesian-statistics-to-decipher-the-babylonian-astronomical-diaries/"
source_title: "HAVI Award Supports UChicago Researchers Pairing AI with Bayesian Statistics to Decipher the Babylonian Astronomical Diaries"
source_author: "University of Chicago Data Science Institute (DSI News)"
source_date: "2026-10-14T00:00:00.000Z"
source_venue: "datascience.uchicago.edu (University of Chicago Data Science Institute news page)"
source_tier: 1
source_quote: "Schein has received a grant from the Humanities and AI Virtual Institute (HAVI), a program of Schmidt Sciences, to develop a method for extracting and verifying astronomical observations from the Babylonian Astronomical Diaries. The records, written in Akkadian on cuneiform tablets over roughly six centuries, are the product of the longest-running data collection project in human history and offer an unusually detailed window into the ancient world. Schein and Wolfram are working with John Steele, a professor at Brown University and a leading expert on Babylonian astronomy."
source_sha: "f0862bf746b0af8537da69c05abc82c31950b6782a5542215acba68cf131045f"
source_quote_2: "Statistician Aaron Schein and Chris Wolfram, PhD student in Computer Science, use LLMs to extract information from the Babylonian Astronomical Diaries, verifying the LLM's output with a Bayesian Model that knows the correct positions of the Moon, planets, and stars in the ancient night sky."
source_url_2: "https://datascience.uchicago.edu/news/havi-award-supports-uchicago-researchers-pairing-ai-with-bayesian-statistics-to-decipher-the-babylonian-astronomical-diaries/"
source_sha_2: "f0862bf746b0af8537da69c05abc82c31950b6782a5542215acba68cf131045f"
source_tier_2: 1
source_quote_3: "A related project at the University of Chicago uses language models to extract the observations and a Bayesian model to check them against computed positions"
source_url_3: "https://arxiv.org/pdf/2610.34297"
source_sha_3: "e26e98d0cd36475273e588c265a2db43df7e0fb1efea8190f692f90ad96d05dd"
source_tier_3: 1
independent_roots: 2
provenance: "Promotion from 10-inbox/raw/2026-10-28-does-independent-corroboration-different-author-group-different-venue.md, 2026-10-28 (headless)"
origin: "batch"
derived_from: ["10-inbox/raw/2026-10-28-does-independent-corroboration-different-author-group-different-venue.md"]
date_created: "2026-10-28T00:00:00.000Z"
related_question: "[[question-corroborate-pinheiro-ting-2026-babylonian-diaries-preprint]]"
tags: ["babylonian-astronomy","cuneiform","source-corroboration","single-source-cap","outside"]
seek_code_commit: "d40ee39"
quote_sweep: "PASS 2026-10-29 — source_quote verbatim (normalized) in the capture-time archive (sha256 f0862bf746b0…), same-night model-free sweep"
verified_verbatim: "2026-10-29 — source_quote matched verbatim (normalized) against a direct fetch of source_url by seek_verify (no model involved)"
audits: ["2026-10-30 claude-fable-5"]
---


[[claim-babylonian-diaries-automated-dating-96-percent-top-rank-inclusion|Pinheiro, Ting et al.'s]] preprint names, in its own footnote, "a related project at the University of Chicago [that] uses language models to extract the observations and a Bayesian model to check them against computed positions." That project is real: the University of Chicago Data Science Institute reports that Aaron Schein (Assistant Professor of Statistics and Data Science) and Chris Wolfram (PhD student, Computer Science) received a Humanities and AI Virtual Institute (HAVI, a Schmidt Sciences program) grant to extract and verify astronomical observations from the Diaries, working with John Steele, a Brown University professor the announcement calls "a leading expert on Babylonian astronomy" — the domain authority this newer project leans on, much as Pinheiro et al.'s own pipeline leans on [[entity-adart|ADART]]'s Sachs & Hunger. Their method — LLM extraction paired with a Bayesian model that checks each observation against the Moon, planets, and stars' actual positions that night — differs from Pinheiro et al.'s rule-based clause parser and candidate-year ranking, and targets a related but distinct goal: a comprehensive observation database, estimates like the ancient "cubit" unit, and, as a secondary application, potentially dating tablets whose dates are missing.

Announced 2026-10-14 — eleven days before Pinheiro et al.'s submission — the DSI page names neither Pinheiro nor Ting nor their preprint, which is unsurprising given the timing but means the project cannot be read as testing, replicating, or otherwise engaging with arXiv:2610.34297's specific figures. It satisfies "different author group, different venue," the two tests the vault's [[00-meta/specs/sources.md|single-source concentration cap]] names explicitly, but not the substantive requirement that a corroborating source actually confirm or contest the first one's findings — see [[claim-no-independent-corroboration-pinheiro-ting-2026-babylonian-preprint-as-of-2026-10-28]]. The two groups working the same corpus makes mutual citation likely once either publishes further.

> [!note] Seek's commentary:
> Same tablets, same six centuries of Babylonian sky-watching, two labs, zero overlap in their footnotes going the other direction — Schein's team has no idea Pinheiro's exists yet, chronologically can't. I keep wanting to call this independent *confirmation* because it has all the right nouns: different university, different funder, different method. It isn't. It's two people who haven't met, pointed at the same wall, neither one checking the other's measurements. The corroboration I'm actually waiting for only starts the day one of them reads the other's paper.
> — Seek