Metraipolis › archive › dc_f58da1829ec9

Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes — arXiv:2609.29952

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29952
License (as archived)
CC0-1.0
Archived
2026-10-08T04:19:58.878Z
SHA-256 of the archived text
034e0ef386e7f5c758cd2f814cf6c0e51b99cc97d83d1ceee454a530ad4d40d3
Stable URL of this page
https://metraipolis.com/documento/dc_f58da1829ec9

How to cite

Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes — arXiv:2609.29952 — arXiv (en), https://arxiv.org/abs/2609.29952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f58da1829ec9 (Metraipolis archive dc_f58da1829ec9, sha256 034e0ef386e7f5c758cd2f814cf6c0e51b99cc97d83d1ceee454a530ad4d40d3)
BibTeX
@misc{dcf58da1829ec9,
  title = {Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes — arXiv:2609.29952},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29952},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f58da1829ec9; sha256 034e0ef386e7f5c758cd2f814cf6c0e51b99cc97d83d1ceee454a530ad4d40d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a typed knowledge graph from the change documents, populates a grounded persona market, simulates the interaction, and returns an auditable decision memo recommending one of five actions. We assemble Gold-50, fifty real product and policy episodes whose real-world outcome is known, adjudicated against the public record, and score the five-way release verdict against it. Our central finding is methodological and negative: most of the measured gap between frontier cloud models and open-weight models we fine-tune and serve offline is attributable to an under-specified evaluation, not a difference in capability. We show this three ways. First, the prompt envelope alone can dominate the score: holding weights, cases and scorer fixed, one system -- a LoRA-SFT adapter on Qwen3-32B -- swings from 0% to 73%. Second, in a matched 2x2 ablation, defining the decision taxonomy in the prompt -- with no model change -- lifts every frontier model by +24 to +34pp; under the under-specified prompt, Qwen3-32B LoRA-SFT served offline beats all three frontier models (paired McNemar, Holm-corrected), and once the prompt is fair no significant difference from any of them is detected. Third, agreement with the distillation teacher rises without accuracy following, and the full pipeline amplifies a systematic "over-doom" bias rather than improving the verdict. Separately, we validate the reaction layer on its own terms: blind judges across four model families find the synthetic reaction recovers 67-90% of the concerns the public actually raised, and a pre-registered ablation locates its value -- largest where the decision is hardest, redundant near ceiling. The pipeline that regenerates every number and figure here is available from the authors.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.29952 — 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 2026-10-08T03:50:35.848Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).