{"paper":{"title":"LLMpedia: A Transparent Framework to Materialize an LLM's Encyclopedic Knowledge at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Muhammed Saeed, Simon Razniewski","submitted_at":"2026-03-25T08:37:26Z","abstract_excerpt":"Benchmarks like MMLU suggest flagship language models approach factuality saturation above 90\\%. \\emph{LLMpedia} shows this picture is incomplete. We materialize ${\\sim}$1.3M encyclopedia articles entirely from parametric memory across three model families, then audit every claim against Wikipedia and curated web evidence. For \\texttt{gpt-5-mini}, the verifiable true rate is 68.4\\% on Wikipedia-covered subjects - more than 21\\,pp below MMLU - and the gap is driven by \\emph{unverifiability} (30.5\\%), not refutation (1.2\\%). Beyond Wikipedia, frontier articles audited against curated web evidenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24080","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.24080/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}