Metraipolis › archive › dc_f34ab1aec593

Evidence-Based Scientific Question Discovery: A Framework with Historical Backtesting — arXiv:2608.09968

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09968
License (as archived)
CC0-1.0
Archived
2026-10-19T06:08:47.864Z
SHA-256 of the archived text
fbe1540c180bf04d3c431b4b27573673b1a32d2f3689c67156386045987c9d94
Stable URL of this page
https://metraipolis.com/documento/dc_f34ab1aec593

How to cite

Evidence-Based Scientific Question Discovery: A Framework with Historical Backtesting — arXiv:2608.09968 — arXiv (en), https://arxiv.org/abs/2608.09968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f34ab1aec593 (Metraipolis archive dc_f34ab1aec593, sha256 fbe1540c180bf04d3c431b4b27573673b1a32d2f3689c67156386045987c9d94)
BibTeX
@misc{dcf34ab1aec593,
  title = {Evidence-Based Scientific Question Discovery: A Framework with Historical Backtesting — arXiv:2608.09968},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09968},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f34ab1aec593; sha256 fbe1540c180bf04d3c431b4b27573673b1a32d2f3689c67156386045987c9d94},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current AI systems are optimized for answering questions; the scientific enterprise is bottlenecked earlier, at discovering the questions worth investigating. We present a framework that turns a traceable, reproducible, scope controlled research corpus into ranked, falsifiable research questions: evidence is represented as provenance carrying claims; cross paper tensions are detected, typed, and human adjudicated; surviving signals are refined into questions and ranked by a two stage protocol separating scientific priority from execution priority. We instantiate the framework on exoplanet atmospheres, a domain that uniquely combines literature, structured catalogs, and space telescope archives. In a historical backtest, all questions generated from evidence available before 2021 were substantively engaged by the 2021 to 2026 literature the sys?tem never saw: two were answered, including one whose premise the community later explicitly refuted and the top ranked question is independently posed and still open. These results sug?gest that systematic question discovery from evidence tensions surfaces the questions working scientists subsequently invest in.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Digital Libraries (cs.DL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.09968 — 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 2026-10-19T05:57:28.321Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).