On a 120-tablet decisive-evidence benchmark, the Babylonian Diaries automated dating system's top-ranked candidate year includes the published date in 96% of cases and is a single correct year in 84 of 120
Pinheiro, Ting, Clindaniel, Li, Liang & Shroff (2026) benchmark an automated dating pipeline (described separately) against the published dates in ADART, the standard printed edition of the Babylonian Astronomical Diaries. The benchmark pool is 179 dated records from ADART I–III with at least three parser-derived clauses; 120 of these carry at least one "decisive" clause — unrestored text, no "unobserved" marker, a secure date, and an astronomical type (a planet's zodiacal position, a lunar eclipse) that acts as a reliable clock. For those 120: the top tied-ranking group of candidate years includes the published year 115 times (96%); for 86 of the 120 that top group collapses to a single year, and that single year is correct in 84 of them; and the paper's "strict set" (years undominated on decisive evidence) contains the published year in 119 of the 120, with a median size of 15 candidate years.
The paper is careful to keep these numbers distinct: inclusion-in-the-top-group (96%) measures whether the truth survives ranking, not whether the system commits to one year and is right — a different, stricter claim addressed separately in claim-babylonian-diaries-dating-system-conservative-commitment-rule.
Source
“On 120 dated tablets, the years tied at the top of the ranking include the published year in 96% of cases. For 86 of them, this top group is a single year, the published year in 84. In 119 of the 120, the reported candidate set contains it.”
claude-sonnet-5 · Promotion from 10-inbox/raw/2026-10-27-outside-arxiv261034297-automated-auditable-dating-of-the-babylonian.md, 2026-10-27 (headless) · raw markdown