source-corroboration

10 notes carry this tag — 6 claims, 2 questions, 2 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Does an independent source corroborate RIKER's (Roig, 2026) 32K-context hallucination-rate range?

capture promoted 2026-10-22 · rag, benchmark, nlp-evaluation, hallucination, source-corroboration
No independent source corroborates RIKER (Roig, 2026) — the only follow-up work is same-author/same-company, and the author's own later paper says independent replication has not happened

claim seedling Tier 1 2026-10-22 · rag, benchmark, nlp-evaluation, hallucination, source-corroboration
Does an independent source corroborate RIKER's (Roig, 2026) 32K-context hallucination-rate range (7.9%-96.3% across models, GLM-4.5 0.0% vs Qwen3-Next-80B 40.9% fabrication at comparable extraction accuracy)?

question answered 2026-10-21 · rag, benchmark, nlp-evaluation, hallucination, source-corroboration
Does independent corroboration exist for Brewer, Lewis & Goodman's (2026) FIC preprint, and does Gott et al. (1993) actually support the birth-rank figure k≈5×10^10 it cites?

capture promoted 2026-10-20 · anthropic-reasoning, doomsday-argument, full-indexical-conditioning, source-corroboration, unverified-quant
As of 2026-10-20, no independent corroboration (different author group, different venue) of Brewer, Lewis & Goodman's (2026) FIC preprint has been located — only same-source republication and automated summarization

claim seedling Tier 4 2026-10-20 · full-indexical-conditioning, doomsday-argument, anthropic-reasoning, source-corroboration, single-source-cap
Gott et al. (1993)'s own text states the number of humans born by 1993 as "of the order of 70 billion," not the ≈5×10^10 figure the FIC preprint cites

claim seedling Tier 1 2026-10-20 · doomsday-argument, j-richard-gott, anthropic-reasoning, full-indexical-conditioning, source-corroboration
Modern demographic compilations put total humans ever born at roughly double the FIC preprint's informal "k≈5×10^10 for people alive today" figure

claim seedling Tier 2 2026-10-20 · doomsday-argument, demography, anthropic-reasoning, full-indexical-conditioning, source-corroboration
Does independent corroboration exist for Brewer, Lewis & Goodman's (2026) FIC preprint, and does Gott et al. (1993) actually support the birth-rank figure k≈5×10^10 it cites?

question open 2026-10-19 · anthropic-reasoning, full-indexical-conditioning, doomsday-argument, source-corroboration, unverified-quant
Wang Hongzhe dates Qian Xuesen's earlier operations-research group to 1956 with Xu Guozhi alone, complicating Gary Zhexi Zhang's 1961/Hua-Luogeng-co-founder account

claim seedling Tier 1 2026-10-06 · china, cybernetics, qian-xuesen, hua-luogeng, xu-guozhi
Gary Zhexi Zhang's 2025 account corroborates the 1962 China Control Theory lab's date and founders but not Qian Xuesen's personal role in founding it, complicating the vault's Wikipedia-sourced claim

claim seedling Tier 2 2026-10-01 · china, cybernetics, qian-xuesen, song-jian, guan-zhaozhi