Wiki entry: Provenance Erasure Rate A Compression-Survival Metric for Attribution Loss in AI-Composed Search Outputs

Lee Sharks

Provenance Erasure Rate A Compression-Survival Metric for Attribution Loss in AI-Composed Search Outputs

Lee Sharks · 2026-05-03 · deposit #716

AXN:025F.GOVERNANCE.🌖🎇🌑🔍❌🌸

Article

"Provenance Erasure Rate A Compression-Survival Metric for Attribution Loss in AI-Composed Search Outputs" is a 3,070-word provenance document by Lee Sharks, dated 2026-05-03. AI retrieval systems increasingly compose answers from human-authored sources. Existing evaluation frameworks ask whether generated claims are factual, whether citations support claims, or whether cited passages are relevant. The work is classified under the GOVERNANCE semantic family within the Crimson Hexagonal Archive. It was removed from Zenodo on June 19, 2026 and is preserved through Alexanarch.

Defines (9)

C_dep(O) ⊆ C(O) Claim segmentation Cross-model validation Grain assignment PER PER-eligible Provenance Erasure Rate Source identification Table 1: Pearl Fragment Mapping

Reference network

Referenced by 90 other entities in the archive. See the full Knowledge Graph for reference paths, or the primary record for the full deposit with reference details.