> For the complete documentation index, see [llms.txt](https://dealers.paveinspect.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dealers.paveinspect.com/additional-features/accuracy-and-limitations.md). # Accuracy & Limitations ## PAVE Grading vs Auction Grading Over the past two years, extensive testing and iterations have been conducted to PAVE's damage detection and grading capabilities with the help of one of North America's largest auto auctions. Below are results from the most recent test completed in November 2020. These 10 vehicles were PAVE'd in the same way you or your customer would use the tool, and then the PAVE reports were compared to the ones generated by the auction's in-person inspections. | | PAVE GRADING | | | AUCTION'S GRADING | | | -- | :----------: | ------------------- | - | :---------------: | ------------- | | 1 | 5 | EXCELLENT CONDITION | | 5 | EXTRA CLEAN | | 2 | 3 | GOOD CONDITION | | 3.7 | AVERAGE | | 3 | 4 | VERY GOOD CONDITION | | 3.7 | CLEAN | | 4 | 2 | FAIR CONDITION | | 3.2 | AVERAGE | | 5 | 2 | FAIR CONDITION | | 2.8 | BELOW AVERAGE | | 6 | 3 | GOOD CONDITION | | 2.8 | AVERAGE | | 7 | 3 | GOOD CONDITION | | 2.8 | AVERAGE | | 8 | 3 | GOOD CONDITION | | 2.8 | AVERAGE | | 9 | 1 | POOR CONDITION | | 1.9 | ROUGH | | 10 | 2 | FAIR CONDITION | | 1.3 | BELOW AVERAGE | These very closely aligned and only differ because PAVE does not use fractions on our Retail use gradings. This comparison reinforces that PAVE's grading will provide you with an idea of what to expect if you run the same vehicle at the auction. ## PAVE Damage Detection Limitations **No Interior Inspections** Our User Acceptance Testing has proven that if a process asks for more than 13 photos, and takes longer than 3 minutes to complete, users will be less likely to complete the process. Capturing all the perspectives needed to do a complete interior inspection using PAVE's approach would not be acceptable to most users. However, the grading algorithm accounts for the interior to be in equal condition to the exterior. Our tests have proven to be accurate when PAVE grades a vehicle as being in Poor Condition, expect that the interior will also be in Poor Condition. **Glass Damage Rarely Shows in Photos** PAVE inspects all glass surfaces for cracks, chips, scratches and stars. On average 70% of these types of damages show up in the captured photos. However, when there are small chips and stars in a windshield, they may not appear in the photos and therefore are unable to be detected by PAVE. **Previous Accident Repairs** Detection of any previous paintwork can only get done effectively by metering the paint with a paint gauge and measuring the thickness of paint on each panel. PAVE will detect any mismatched paintwork and any panels that are misaligned. We recommend that you pull a vehicle history report to check for any reported accidents. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://dealers.paveinspect.com/additional-features/accuracy-and-limitations.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.