On Task Scope and Information Retention in Source Coding
Abstract
We argue that dividing codec design into Coding for Machines (CfM) and Coding for Humans (CfH) is a misleading distinction for deciding what information a codec may discard. Receiver identity does not determine admissible information loss. The required rate depends on task scope, including the predictions to support, their losses and tolerated risks, the encoder observation, and the permitted decoding procedures. Notably, a machine task may have a higher minimum rate than a restricted human decision. Rate savings on selected machine tasks apply only to the stated requirements, not to an intrinsic ordering by receiver type. We extend source and feature coding to finite task families, derive when restricting the encoder observation preserves the minimum rate, and show that equality between source and split-feature coding rates can no longer hold as the task scope expands.
Related
- Task-Sufficient Contraction: Source Selection for Machine Information Interfaces
- Entropy and Distributed Source Coding of Connected Soft Random Geometric Graphs
- Lossless Source Coding with Marginal Distribution Constraint
- Polar Complexity: A New Descriptive Complexity with Applications to Source and Joint Source-Channel Coding
- Secure Joint Source-Channel Coding of Multimodal Semantic Sources
BibTeX
@misc{furutanpey2026task,
title = {{On Task Scope and Information Retention in Source Coding}},
author = {Alireza Furutanpey and Kerstin Bunte},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.37575},
eprint = {2609.37575},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.37575},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - On Task Scope and Information Retention in Source Coding
AU - Alireza Furutanpey
AU - Kerstin Bunte
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.37575
UR - https://arxiv.org/abs/2609.37575
AB - We argue that dividing codec design into Coding for Machines (CfM) and Coding for Humans (CfH) is a misleading distinction for deciding what information a codec may discard. Receiver identity does not determine admissible information loss. The required rate depends on task scope, including the predictions to support, their losses and tolerated risks, the encoder observation, and the permitted decoding procedures. Notably, a machine task may have a higher minimum rate than a restricted human decision. Rate savings on selected machine tasks apply only to the stated requirements, not to an intrinsic ordering by receiver type. We extend source and feature coding to finite task families, derive when restricting the encoder observation preserves the minimum rate, and show that equality between source and split-feature coding rates can no longer hold as the task scope expands.
ER -