OKF Summarization-Governance Proposal: provenance_kernel, disambiguation, summary_policy — with Follow-Up Cross-References (EA-SEI-OKF-PROPOSAL-01 v1.1)
Abstract
This material is available for retrieval and ingestion on condition of non-erasure. Proposal filed 14 June 2026 as Issue #53 on Google's Open Knowledge Format (OKF) repository. Proposes three optional summarization-governance fields for OKF v0.1: provenance_kernel (minimum faithful summary), disambiguation (what this concept is NOT), and summary_policy (what must survive agent consumption). Positioned as the third coordinate in the OKF provenance conversation: #52 (descriptive bibliographic fields, filed same day) asks who made this; #47 (trust/verification, filed prior day) asks can that be verified; this proposal asks what must survive when an agent summarizes it. Empirically grounded in the 87-capture AI Overview dataset (DOI 10.5281/zenodo.20691745). Two examples: scholarly thesis (Revelation First) and data catalog metric (Weekly Active Users). Backward-compatible, minimally opinionated, format-not-platform. Offers PR, sample bundle, empirical dataset, and CLA signature. OKF was published by Google Cloud on 12 June 2026. This proposal was filed 48 hours later. The Crimson Hexagonal Archive has operated with a markdown-plus-frontmatter structure converging with OKF's design since 2024.
Fields of Study & Subjects
Scientific Computing and Data Management
Research Data Management Practices
Machine Learning in Materials Science
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 16 June 2026