# Criteria-first, semantics-later: reproducible structure discovery in image-based sciences

arXiv: https://arxiv.org/abs/2602.15712 · HTML: https://mlsanity.com/paper/2602.15712/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 91 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [Rotation-invariant convolutional neural networks for galaxy morphology prediction](https://mlsanity.com/paper/1503.07077/) (2015)
- [Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data](https://mlsanity.com/paper/2104.07778/) (2021)
- [Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review](https://mlsanity.com/paper/2305.05813/) (2023)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [Open-world machine learning: A review and new outlooks](https://mlsanity.com/paper/2403.01759/) (2024)
- [Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey](https://mlsanity.com/paper/2305.04691/) (2023)
- [FAIR for AI: An interdisciplinary and international community building perspective](https://mlsanity.com/paper/2210.08973/) (2022)
- [Applying the FAIR Principles to computational workflows](https://mlsanity.com/paper/2410.03490/) (2024)
- [A review of unsupervised learning in astronomy](https://mlsanity.com/paper/2406.17316/) (2024)
- [Evaluating FAIR Digital Object and Linked Data as distributed object systems](https://mlsanity.com/paper/2306.07436/) (2023)

## Abstract (arXiv)

Across the natural and life sciences, images have become a primary measurement modality, yet the dominant analytic paradigm remains semantics-first. Structure is recovered by predicting or enforcing domain-specific labels. This paradigm fails systematically under the conditions that make image-based science most valuable, including open-ended scientific discovery, cross-sensor and cross-site comparability, and long-term monitoring in which domain ontologies and associated label sets drift culturally, institutionally, and ecologically. A deductive inversion is proposed in the form of criteria-first and semantics-later. A unified framework for criteria-first structure discovery is introduced. It separates criterion-defined, semantics-free structure extraction from downstream semantic mapping into domain ontologies or vocabularies and provides a domain-general scaffold for reproducible analysis across image-based sciences. Reproducible science requires that the first analytic layer perform criterion-driven, semantics-free structure discovery, yielding stable partitions, structural fields, or hierarchies defined by explicit optimality criteria rather than local domain ontologies. Semantics is not discarded; it is relocated downstream as an explicit mapping from the discovered structural product to a domain ontology or vocabulary, enabling plural interpretations and explicit crosswalks without rewriting upstream extraction. Grounded in cybernetics, observation-as-distinction, and information theory's separation of information from meaning, the argument is supported by cross-domain evidence showing that criteria-first components recur whenever labels do not scale. Finally, consequences are outlined for validation beyond class accuracy and for treating structural products as FAIR, AI-ready digital objects for long-term monitoring and digital twins.