# On Task Scope and Information Retention in Source Coding

arXiv: https://arxiv.org/abs/2609.37575 · HTML: https://mlsanity.com/paper/2609.37575/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2107.08373/) (2021)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [Supervised Compression for Resource-Constrained Edge Computing Systems](https://mlsanity.com/paper/2108.11898/) (2021)
- [Image Coding for Machines with Omnipotent Feature Learning](https://mlsanity.com/paper/2207.01932/) (2022)
- [SC2 Benchmark: Supervised Compression for Split Computing](https://mlsanity.com/paper/2203.08875/) (2022)
- [Rate-Distortion Theory in Coding for Machines and its Application](https://mlsanity.com/paper/2305.17295/) (2023)
- [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023)
- [Pragmatic Image Compression for Human-in-the-Loop Decision-Making](https://mlsanity.com/paper/2108.04219/) (2021)
- [FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression](https://mlsanity.com/paper/2403.16677/) (2024)
- [DT-UFC: Universal Large Model Feature Coding via Peaky-to-Balanced Distribution Transformation](https://mlsanity.com/paper/2506.16495/) (2025)
- [Le Cam meets LeCun: Deficiency and Generic Feature Learning](https://mlsanity.com/paper/1402.4884/) (2014)
- [Towards Task-Compatible Compressible Representations](https://mlsanity.com/paper/2405.10244/) (2024)
- [Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding](https://mlsanity.com/paper/2602.12866/) (2026)
- [Task-Aware Answer Preservation under Audio Compression for Large Audio Language Models](https://mlsanity.com/paper/2605.06631/) (2026)
- [Bayes-Sufficient Representations in Supervised Learning](https://mlsanity.com/paper/2606.04045/) (2026)
- [Machines Serve Human: A Novel Variable Human-machine Collaborative Compression Framework](https://mlsanity.com/paper/2511.08915/) (2025)
- [Lossy Common Information in a Learnable Gray-Wyner Network](https://mlsanity.com/paper/2601.21424/) (2026)
- [Source-Side Sufficiency for the Information Bottleneck: Exact Reduction and Finite-Block Equivalence](https://mlsanity.com/paper/2604.26744/) (2026)

## Abstract (arXiv)

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.