Which sources does Google AI Overviews cite most among Logistics & Freight sources?

Release mri_score_v2.1+2026-10-25+9c34b2dccc04; methodology mri_score_v2.1; generated 2026-10-25; window 2026-05-10 to 2026-10-25; artifact 9f1a507f84e8.

The release roster names no model for Google AI Overviews.

Google AI Overviews's sample is 1,184 observed runs across 102 dates. The evidence floor is 10 observed runs and 7 distinct dates.

ChatGPT runs. They go through OpenAI's API with web search switched on, using the model each release names in its engine roster: gpt-4.1-mini-2025-04-14 in current releases, while earlier runs in the window were answered by gpt-4o-mini-search-preview-2025-03-11. That is the retrieval layer apps and research agents built on OpenAI's API use. The signed-in ChatGPT app answers with its own models and search pipeline and cites differently: a preprint submitted on 2026-10-11 and not yet peer reviewed found that Google Search and OpenAI's API on comparable models together recovered about half of the hostnames ChatGPT Web cited (48.7 and 50.3 percent on two model settings) and 26 to 28 percent of its exact URLs (arXiv 2610.15382v1). Claude, Gemini and Perplexity runs are likewise API runs with web search, on the models the roster names.

Method note, 2026-09-25. From that date, Google AI Mode and Google AI Overviews runs come through a different collection path than earlier runs, with no overlapping days, and answers collected on the two paths differ in how many distinct domains each cites. Per-answer figures for those two engines are read within one side of 2026-09-25, not as a trend across it.

Degraded coverage: 5 of 6 answer engines are currently returning citation-bearing answers. gemini quiet (5 of 20 collected calls produced an observation, 25%). Coverage across the window is uneven: gemini returned citation-bearing answers on 140 of 162 observed days (2,197 of 6,962 returned runs produced a citation); google_ai_mode returned citation-bearing answers on 119 of 162 observed days (1,613 of 2,086 returned runs produced a citation); google_ai_overviews returned citation-bearing answers on 102 of 162 observed days (963 of 1,446 returned runs produced a citation). Engines below 90% of the window are named here; per-engine day and run counts for all 6 are in engine_roster.