PulseAugur
EN
LIVE 08:51:14

Gemini 3.1-pro-preview brand mentions show durability over 20 days

A pre-registered study tested the durability of brand mentions in Gemini's answers over a 20-day period. Researchers sent identical prompts to Gemini 3.1-pro-preview in three waves and found that forecasts based on earlier mentions remained accurate. The model consistently reported its version and did not use search queries despite the feature being enabled, with a human review confirming the accuracy of the automated labeling. AI

IMPACT Demonstrates the stability of LLM output over time, which is crucial for applications relying on consistent information retrieval.

RANK_REASON Academic paper detailing a specific model's behavior. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Gemini 3.1-pro-preview brand mentions show durability over 20 days

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a specific model's behavior. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
39 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Twenty Days Later: A Pre-Registered Test of History-Based Forecasts of Brand Mentions in Gemini Answers

    Counts of which brands a large language model names are useful only if they hold long enough to act on. We test this with a pre-registered replication. The same 162 requests (54 questions in English, Estonian and Finnish about three software categories, four of twelve candidate b…