# Summary of S4-260185: Call Flow for Split Inferencing Loop

## Document Metadata
- **Source:** Interdigital Finland Oy
- **Meeting:** TSG-SA4 Meeting #135, Goa, India (9-13 February 2026)
- **Work Item:** AIML_IMS-MED
- **Type:** Change Request / Text Proposal

## Main Technical Contribution

This contribution proposes a call flow for **split inferencing** operations between the UE and DCAS (Data Collection and Analytics Server), building upon previous work in TR 26.927 and earlier contributions.

### Split Inferencing Architecture

The proposed call flow describes a collaborative inference execution model where:
- The UE and DCAS jointly execute an inference task
- The inference workload is split between the two entities
- Intermediate inference results are exchanged over the user plane
- Communication is facilitated through the MF (Media Function)

### Proposed Call Flow Steps

The text proposal adds the following procedural steps:

1. **Configuration Phase**
   - UE and DCAS (via MF) configure intermediate data format parameters over ADC (Application Data Collection)
   - Parameters include tensor characteristics and compression profile identifiers

2. **UE-Side Processing**
   - UE captures input media data
   - UE executes its inference subtask using the selected UE submodel
   - UE generates intermediate data for continuation at DCAS

3. **Data Exchange**
   - UE transmits intermediate data to DCAS (via MF) according to configured format

4. **DCAS-Side Processing**
   - DCAS executes its inference task on received intermediate data
   - DCAS uses selected Remote submodel
   - DCAS generates processed media data based on inference results

5. **Result Delivery**
   - DCAS transmits processed media data to UE (via MF)
   - UE renders the final processed media data

## Technical Significance

This proposal enables **distributed AI/ML inference** for media processing, allowing workload distribution between device and network based on computational capabilities, latency requirements, and network conditions. The standardization of intermediate data format parameters ensures interoperability in split inference scenarios.