Metraipolis › archive › dc_2802bea852b7

Time Capsule of Testable Human Knowledge: 41 Years of Jeopardy! in a Single Free Local Model — arXiv:2608.27459

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27459
License (as archived)
CC0-1.0
Archived
2026-10-17T10:43:23.309Z
SHA-256 of the archived text
134aee945dbb53f135718e3687343e005932ecc3e051df3ec9f124b32cf59361
Stable URL of this page
https://metraipolis.com/documento/dc_2802bea852b7

How to cite

Time Capsule of Testable Human Knowledge: 41 Years of Jeopardy! in a Single Free Local Model — arXiv:2608.27459 — arXiv (en), https://arxiv.org/abs/2608.27459 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2802bea852b7 (Metraipolis archive dc_2802bea852b7, sha256 134aee945dbb53f135718e3687343e005932ecc3e051df3ec9f124b32cf59361)
BibTeX
@misc{dc2802bea852b7,
  title = {Time Capsule of Testable Human Knowledge: 41 Years of Jeopardy! in a Single Free Local Model — arXiv:2608.27459},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27459},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2802bea852b7; sha256 134aee945dbb53f135718e3687343e005932ecc3e051df3ec9f124b32cf59361},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27459. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In 2011, IBM's Watson was something like a sealed capsule of its era's queryable knowledge. Its DeepQA system defeated the strongest human Jeopardy! champions, but the knowledge that let it do so lived in a curated billion-document corpus running on a cluster of POWER7 servers, frozen at build time and impossible to move or copy. We show that the same kind of artifact, a snapshot of what a culture can answer, is now portable and essentially free. We evaluate a single 9 GB open-weight model (Qwen2.5-14B, 4-bit) against the complete open Jeopardy! clue dataset, 529,939 clues across all 41 broadcast seasons from 1984 to 2025. To our knowledge this is the first time a model has been run over the full corpus. The 41 years mark only how long the questions were collected. What they test is far older and broader: the accumulated body of human general knowledge a culture considers worth knowing, from ancient history and dead languages to science, literature, and geography, with a verified answer for every item. The model answers 67.0% of all clues under a strict forced-response protocol with exact and fuzzy matching, and exceeds 85% on factoid categories. We treat training-data exposure as something both systems share rather than a flaw unique to language models. Watson's case is in fact the more extreme one. Its corpus was assembled to contain Jeopardy answers and it was tuned on past clues, and it could not answer anything outside that curated distribution. The decisive test is whether a model can answer clues that did not exist when it was built. On clues aired after its training cutoff, the local model holds 65% and Claude Opus 4.8 holds 95%, while Watson by construction scores zero. The capability survives the move from a server room to a file you could seal in a time capsule, and unlike Watson it is not frozen to its own moment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.27459 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T10:33:42.315Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).