R1-2410203
discussion
Discussions on other aspects of AlML In NR air interface
From TCL
Summary
TCL presents a discussion on AI/ML framework aspects for NR air interface, focusing on model identification and additional conditions management. The document contains 3 observations and 3 proposals addressing ID hierarchical relationships, functional overlaps, and overhead reduction strategies.
Position
TCL advocates FOR a hierarchical ID structure where model IDs represent generic model types rather than specific trained models to reduce overhead, and FOR eliminating duplicate ID definitions between associated ID and dataset ID. They push AGAINST maintaining large numbers of specific model IDs and AGAINST ambiguous cross-cell ID mappings without explicit definitions.
Key proposals
- Proposal 1 (Sec 2.1): The functionality ID corresponds to the use cases or sub use cases. The model ID corresponds to a model type or model structure, not a specific model trained by a specific dataset.
- Proposal 2 (Sec 2.1): The associated ID and the dataset ID are functional overlap and can be mutually substituted, they may not be duplicated defined.
- Proposal 3 (Sec 2.2): If the associated ID is globally or cross-cell defined, an explicit mapping between the associated ID and the NW additional conditions should be defined.