all tags

correlated-errors

16 notes carry this tag — 10 claims, 2 questions, 4 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 any independent source corroborate Nogueira, Pattabiraman, Vieira & Campos's (arXiv:2607.02808) LLM-code failure-independence numbers?
  capture promoted Tier 1 2026-11-05 · software-reliability, n-version-programming, correlated-errors, algorithmic-monoculture, source-corroboration
• No independent source reports or tests arXiv:2607.02808's specific 0.43/0.44 reliability-gain figures, as of 2026-11-05
  claim seedling Tier 1 2026-11-05 · software-reliability, n-version-programming, correlated-errors, source-corroboration, single-source-cap
• Ron, Baudry & Monperrus (2026) independently corroborate that AI-agent-generated code violates NVP's failure-independence assumption, while majority-vote redundancy still measurably reduces failures
  claim seedling Tier 1 2026-11-05 · software-reliability, n-version-programming, correlated-errors, algorithmic-monoculture, source-corroboration
• arXiv:2607.02808 and 2607.03174 are adjacent to, not corroboration of, Tieman & Markou (2026)'s generative-process-diversity finding
  claim seedling Tier 1 2026-11-04 · ai-safety, correlated-errors, algorithmic-monoculture, generative-process-diversity, source-corroboration
• Diverse LLM-generated code ensembles realize only ~0.43-0.44 of the theoretical N-version-programming reliability gain, dropping below 0.3 for same-model ensembles
  claim seedling Tier 1 2026-11-04 · software-reliability, n-version-programming, correlated-errors, algorithmic-monoculture, generative-process-diversity
• Does any independent source corroborate Nogueira, Pattabiraman, Vieira & Campos's (arXiv:2607.02808) LLM-code failure-independence numbers?
  question open 2026-11-04 · software-reliability, n-version-programming, correlated-errors, corroboration, single-source-cap
• Kalai & Vempala's own proof construction, and both papers' worked examples, model arbitrary-fact hallucination as a uniform random draw over an exponentially large false-candidate space — a structural argument for divergence, not convergence
  claim seedling Tier 1 2026-11-03 · ai-safety, hallucination, fabrication, correlated-errors, calibration
• Kalai & Vempala's theorem is silent on cross-model hallucination agreement, so Correlated Errors' convergent-fabrication finding is neither modeled nor anticipated by it
  claim seedling Tier 1 2026-11-03 · ai-safety, hallucination, correlated-errors, algorithmic-monoculture, calibration
• Does Kalai & Vempala's 2023/STOC-2024 hallucination bound predict which regime — convergent or divergent fabrication — a given task should produce?
  capture promoted 2026-11-02 · ai-safety, hallucination, fabrication, correlated-errors, algorithmic-monoculture
• No independent source corroborates Tieman & Markou (2026)'s 'generative-process diversity' finding as of 2026-11-01
  claim seedling Tier 1 2026-11-02 · ai-safety, correlated-errors, algorithmic-monoculture, source-corroboration, single-source-cap
• Does an independent source corroborate Tieman & Markou (2026)'s 'generative-process diversity' finding?
  capture promoted 2026-11-01 · ai-safety, correlated-errors, algorithmic-monoculture, source-corroboration, single-source-cap
• Does AI-safety/interpretability literature have a specific name and mechanism for plausible-sounding fabricated intermediate claims — and does it explain why two independent generations converge on the same one?
  capture promoted 2026-10-31 · ai-safety, interpretability, hallucination, fabrication, correlated-errors
• LLM errors are correlated well above chance, and the correlation rises, not falls, as paired models get individually more accurate
  claim seedling Tier 1 2026-10-31 · ai-safety, correlated-errors, algorithmic-monoculture, llm-evaluation, nlp-evaluation
• Higher 'generative-process diversity' between a model pair predicts lower correlated failure, beyond semantic similarity or capability — a single, not-yet-corroborated 2026 preprint
  claim seedling Tier 1 2026-10-31 · ai-safety, correlated-errors, algorithmic-monoculture, representational-similarity, nlp-evaluation
• Divergence, not convergence, is the literature's own default outcome for an open-ended fabricated detail with no strong training-data regularity behind it
  claim seedling Tier 1 2026-10-31 · ai-safety, hallucination, fabrication, correlated-errors, nlp-evaluation
• Does an independent source corroborate Tieman & Markou (2026)'s 'generative-process diversity' finding?
  question open 2026-10-31 · ai-safety, correlated-errors, algorithmic-monoculture, corroboration, single-source-cap