CATT · 9.1.3
Specification support for CSI prediction ·
RAN1#120 · Source verification
Claude's delta
shifted
vs RAN1#119
CATT preserved its stance on negligible impact of tilt/TXRU but refined its position by adding specific proposals for a new processing unit type or enhanced CPU separate from the legacy pool. They added a requirement to distinguish AI/ML CSI reports via a new report quantity or identifier. Their monitoring preference was consolidated to explicitly prefer SGCS for Type 1 and Type 3 while deprioritizing Type 2, moving from general monitoring advocacy to specific metric and resource definitions.
AI-synthesized from contributions · all text is paraphrased
Every position summary on this site is generated by an AI from the actual Tdoc contributions. This page shows you the exact source documents Claude read to produce the summary above, so you can verify it yourself. Click any Tdoc ID to view its detail page, or click "3gpp.org ↗" to read the original on the official 3GPP server.
Contributions at RAN1#120 · 1 doc
Discussion on AI/ML-based CSI prediction
Position extracted by Claude
CATT concludes that consistency between training and inference regarding antenna down tilt and TXRU mapping is not required, citing simulation results showing negligible performance impact on SGCS. They propose introducing a new processing unit type or enhanced CPU for AI/ML-based CSI processing, which is separately counted from the legacy CPU pool but shared among CSI-related AI/ML functionalities. CATT supports distinguishing AI/ML CSI reports from legacy reports via a new report quantity or identifier. For performance monitoring, they prefer SGCS as the metric for Type 1 and Type 3 monitoring and explicitly deprioritize Type 2 monitoring due to high overhead and quantization errors. They propose reusing the CSI framework for monitoring configuration, allowing either reuse of inference resources or dedicated monitoring resources.
Summary
CATT presents simulation results demonstrating that antenna tilt angles and TXRU mappings have negligible impact on UE-sided CSI prediction performance, concluding that strict consistency between training and inference for these parameters is unnecessary. The document proposes introducing a new processing unit type for AI/ML inference, distinguishing AI/ML reports from legacy ones, and deprioritizing Type 2 performance monitoring due to overhead and accuracy concerns, while supporting SGCS as the metric for Type 1 and Type 3 monitoring.
Prior contributions at RAN1#119 · 1 doc · Nov 18, 2024
Specification support for AI/ML-based CSI prediction
Position extracted by Claude
CATT advocates FOR relaxing consistency requirements for network-side antenna configurations (tilt angles, TXRU mapping) since they show negligible performance impact, while pushing FOR performance monitoring-based methods to handle other consistency factors like interference distributions that cannot be addressed through associated IDs. They are positioning AGAINST overly restrictive consistency requirements that would unnecessarily complicate CSI prediction implementations.
Summary
CATT's document analyzes consistency requirements between training and inference phases for AI/ML-based CSI prediction in 5G NR networks. The document presents 3 observations and 3 proposals, demonstrating through simulations that network-side conditions like antenna tilt and TXRU mapping have negligible impact, while interference distributions significantly affect performance.
How this was derived
Claude extracted the "position extracted" field above directly from each Tdoc during summarization.
For the delta summary at the top, Claude compared CATT's consolidated stance at RAN1#120
against their stance at RAN1#119 and classified the change as
shifted.
Always verify critical claims against the original Tdocs linked above.